From f3bac0c448771ce4ce94ec9c4e0b5c7dd1469824 Mon Sep 17 00:00:00 2001 From: Ken Qu Date: Tue, 23 Apr 2024 13:31:42 +1000 Subject: [PATCH] update website --- index.html | 345 +++++++++++ script/input.txt | 176 ++---- script/output.txt | 1286 ++++++++++----------------------------- script/translator.ipynb | 1083 ++------------------------------- 4 files changed, 748 insertions(+), 2142 deletions(-) diff --git a/index.html b/index.html index 4a241f9..70e39f5 100644 --- a/index.html +++ b/index.html @@ -105,6 +105,351 @@ Total number of rows: XX + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
TitleVenueYearCodeTarget ExplanationsAttacksDefenses
Please Tell Me More: Privacy Impact of Explainability through the Lens of Membership Inference Attack2024SPFeature-basedMembership InferenceDifferential Privacy, Privacy-Preserving Models, DP-SGD-
On the Privacy Risks of Algorithmic Recourse2023AISTATSCounterfactualMembership InferenceDifferential Privacy-
The Privacy Issue of Counterfactual Explanations: Explanation Linkage Attacks2023TISTCounterfactualLinkageAnonymisaion-
Feature-based Learning for Diverse and Privacy-Preserving Counterfactual Explanations2023KDDCounterfactual-Perturbation[Code]
Private Graph Extraction via Feature Explanations2023PETSFeature-basedGraph ExtractionPerturbation[Code]
Privacy-Preserving Algorithmic Recourse2023ICAIFCounterfactual-Differential Privacy-
Accurate, Explainable, and Private Models: Providing Recourse While Minimizing Training Data Leakage2023ICML-WorkshopCounterfactualMembership InferenceDifferential Privacy-
Probabilistic Dataset Reconstruction from Interpretable Models2023arXivInterpretable SurrogatesData Reconstruction-[Code]
DeepFixCX: Explainable privacy-preserving image compression for medical image analysis2023WIREs-DMKDCase-basedIdentity recognitionAnonymisation[Code]
XorSHAP: Privacy-Preserving Explainable AI for Decision Tree Models2023PreprintShapley-Multi-party Computation-
-2023GithubALE plot-Differential Privacy[Code]
Inferring Sensitive Attributes from Model Explanations2022CIKMGradient-based, Perturbation-basedAttribute Inference-[Code]
Model explanations with differential privacy2022FAccTFeature-based-Differential Privacy-
DualCF: Efficient Model Extraction Attack from Counterfactual Explanations2022FAccTCounterfactualModel Extraction--
Feature Inference Attack on Shapley Values2022CCSShapleyAttribute/Feature InferenceLow-dimensional-
Evaluating the privacy exposure of interpretable global explainers2022CogMIInterpretable SurrogatesMembership Inference--
Privacy-Preserving Case-Based Explanations: Enabling Visual Interpretability by Protecting Privacy2022IEEE AccessExample-based-Anonymisation-
On the amplification of security and privacy risks by post-hoc explanations in machine learning models2022arXivFeature-basedMembership Inference--
Differentially Private Counterfactuals via Functional Mechanism2022arXivCounterfactual-Differential Privacy-
Differentially Private Shapley Values for Data Evaluation2022arXivShapley-Differential Privacy[Code]
Exploiting Explanations for Model Inversion Attacks2021ICCVGradient-based, Interpretable SurrogatesModel Inversion--
On the Privacy Risks of Model Explanations2021AIESFeature-based, Shapley, CounterfactualMembership Inference--
Adversarial XAI Methods in Cybersecurity2021TIFSCounterfactualMembership Inference--
MEGEX: Data-Free Model Extraction Attack against Gradient-Based Explainable AI2021arXivGradient-basedModel Extraction-[Code]
Robust Counterfactual Explanations for Privacy-Preserving SVM2021ICML-WorkshopCounterfactual-Private SVM[Code]
When Differential Privacy Meets Interpretability: A Case Study2021RCV-CVPRInterpretable Models-Differential Privacy-
Differentially Private Quantiles2021ICMLQuantiles-Differential Privacy[Code]
FOX: Fooling with Explanations : Privacy Protection with Adversarial Reactions in Social Media2021PST-Attribute InferencePrivacy-Protecting Explanation-
Privacy-preserving generative adversarial network for case-based explainability in medical image analysis2021IEEE AccessExample-based-Generative Anonymisation-
Interpretable and Differentially Private Predictions2020AAAILocally linear maps-Differential Privacy[Code]
Model extraction from counterfactual explanations2020arXivCounterfactualModel Extraction-[Code]
Model Reconstruction from Model Explanations2019FAT*Gradient-basedModel Reconstruction, Model Extraction--
Interpret Federated Learning with Shapley Values2019-Shapley-Federated[Code]
Collaborative Explanation of Deep Models with Limited Interaction for Trade Secret and Privacy Preservation2019WWWFeature-based-Collaborative rule-based model-
Model inversion attacks that exploit confidence information and basic countermeasures2015CCSConfidence scoresReconstruction, Model Inversion--
+ + + + + + III. Citations diff --git a/script/input.txt b/script/input.txt index 00a7d70..9dff662 100644 --- a/script/input.txt +++ b/script/input.txt @@ -1,141 +1,35 @@ -Model-Agnostic -| [Towards Adversarial Evaluations for Inexact Machine Unlearning](https://arxiv.org/abs/2201.06640) | 2023 | Goel et al. | _arXiv_ | EU-k, CF-k | [[Code]](https://github.com/shash42/Evaluating-Inexact-Unlearning) | -| [KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment](https://arxiv.org/abs/2305.06535) | 2023 | Wang et al. | _arXiv_ | KGA | [[Code]](https://github.com/Lingzhi-WANG/KGAUnlearn) | | -| [On the Trade-Off between Actionable Explanations and the Right to be Forgotten](https://openreview.net/pdf?id=HWt4BBZjVW) | 2023 | Pawelczyk et al. | _arXiv_ | - | - | | -| [Towards Unbounded Machine Unlearning](https://arxiv.org/pdf/2302.09880) | 2023 | Kurmanji et al. | _arXiv_ | SCRUB | [[Code]](https://github.com/Meghdad92/SCRUB) | approximate unlearning | -| [Netflix and Forget: Efficient and Exact Machine Unlearning from Bi-linear Recommendations](https://arxiv.org/abs/2302.06676) | 2023 | Xu et al. | _arXiv_ | Unlearn-ALS | - | Exact Unlearning | -| [To Be Forgotten or To Be Fair: Unveiling Fairness Implications of Machine Unlearning Methods](https://arxiv.org/abs/2302.03350) | 2023 | Zhang et al. | _arXiv_ | - | [[Code]](https://github.com/cleverhans-lab/machine-unlearning) | | -| [Sequential Informed Federated Unlearning: Efficient and Provable Client Unlearning in Federated Optimization](https://arxiv.org/abs/2211.11656) | 2022 | Fraboni et al. | _arXiv_ | SIFU | - | | -| [Certified Data Removal in Sum-Product Networks](https://arxiv.org/abs/2210.01451) | 2022 | Becker and Liebig | _ICKG_ | UNLEARNSPN | [[Code]](https://github.com/ROYALBEFF/UnlearnSPN) | Certified Removal Mechanisms | -| [Learning with Recoverable Forgetting](https://arxiv.org/abs/2207.08224) | 2022 | Ye et al. | _ECCV_ | LIRF | - | | -| [Continual Learning and Private Unlearning](https://arxiv.org/abs/2203.12817) | 2022 | Liu et al. | _CoLLAs_ | CLPU | [[Code]](https://github.com/Cranial-XIX/Continual-Learning-Private-Unlearning) | | -| [Verifiable and Provably Secure Machine Unlearning](https://arxiv.org/abs/2210.09126) | 2022 | Eisenhofer et al. | _arXiv_ | - | [[Code]](https://github.com/cleverhans-lab/verifiable-unlearning) | Certified Removal Mechanisms | -| [VeriFi: Towards Verifiable Federated Unlearning](https://arxiv.org/abs/2205.12709) | 2022 | Gao et al. | _arXiv_ | VERIFI | - | Certified Removal Mechanisms | -| [FedRecover: Recovering from Poisoning Attacks in Federated Learning using Historical Information](https://arxiv.org/abs/2210.10936) | 2022 | Cao et al. | _S&P_ | FedRecover | - | recovery method | -| [Fast Yet Effective Machine Unlearning](https://arxiv.org/abs/2111.08947) | 2022 | Tarun et al. | _arXiv_ | UNSIR | - | | -| [Membership Inference via Backdooring](https://arxiv.org/abs/2206.04823) | 2022 | Hu et al. | _IJCAI_ | MIB | [[Code]](https://github.com/HongshengHu/membership-inference-via-backdooring) | Membership Inferencing | -| [Forget Unlearning: Towards True Data-Deletion in Machine Learning](https://arxiv.org/abs/2210.08911) | 2022 | Chourasia et al. | _ICLR_ | - | - | noisy gradient descent | -| [Zero-Shot Machine Unlearning](https://arxiv.org/abs/2201.05629) | 2022 | Chundawat et al. | _arXiv_ | - | - | | -| [Efficient Attribute Unlearning: Towards Selective Removal of Input Attributes from Feature Representations](https://arxiv.org/abs/2202.13295) | 2022 | Guo et al. | _arXiv_ | attribute unlearning | - | | -| [Few-Shot Unlearning](https://download.huan-zhang.com/events/srml2022/accepted/yoon22fewshot.pdf) | 2022 | Yoon et al. | _ICLR_ | - | - | | -| [Federated Unlearning: How to Efficiently Erase a Client in FL?](https://arxiv.org/abs/2207.05521) | 2022 | Halimi et al. | _UpML Workshop_ | - | - | federated learning | -| [Machine Unlearning Method Based On Projection Residual](https://arxiv.org/abs/2209.15276) | 2022 | Cao et al. | _DSAA_ | - | - | Projection Residual Method | -| [Hard to Forget: Poisoning Attacks on Certified Machine Unlearning](https://ojs.aaai.org/index.php/AAAI/article/view/20736) | 2022 | Marchant et al. | _AAAI_ | - | [[Code]](https://github.com/ngmarchant/attack-unlearning) | Certified Removal Mechanisms | -| [Athena: Probabilistic Verification of Machine Unlearning](https://web.archive.org/web/20220721061150id_/https://petsymposium.org/popets/2022/popets-2022-0072.pdf) | 2022 | Sommer et al. | _PoPETs_ | ATHENA | - | | -| [FP2-MIA: A Membership Inference Attack Free of Posterior Probability in Machine Unlearning](https://link.springer.com/chapter/10.1007/978-3-031-20917-8_12) | 2022 | Lu et al. | _ProvSec_ | FP2-MIA | - | inference attack | -| [Deletion Inference, Reconstruction, and Compliance in Machine (Un)Learning](https://arxiv.org/abs/2202.03460) | 2022 | Gao et al. | _PETS_ | - | - | | -| [Prompt Certified Machine Unlearning with Randomized Gradient Smoothing and Quantization](https://openreview.net/pdf?id=ue4gP8ZKiWb) | 2022 | Zhang et al. | _NeurIPS_ | PCMU | - | Certified Removal Mechanisms | -| [The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining](https://arxiv.org/abs/2203.07320) | 2022 | Liu et al. | _INFOCOM_ | - | [[Code]](https://github.com/yiliucs/federated-unlearning) | | -| [Backdoor Defense with Machine Unlearning](https://arxiv.org/abs/2201.09538) | 2022 | Liu et al. | _INFOCOM_ | BAERASER | - | Backdoor defense | -| [Markov Chain Monte Carlo-Based Machine Unlearning: Unlearning What Needs to be Forgotten](https://dl.acm.org/doi/abs/10.1145/3488932.3517406) | 2022 | Nguyen et al. | _ASIA CCS_ | MCU | - | MCMC Unlearning | -| [Federated Unlearning for On-Device Recommendation](https://arxiv.org/abs/2210.10958) | 2022 | Yuan et al. | _arXiv_ | - | - | | -| [Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher](https://arxiv.org/abs/2205.08096) | 2022 | Chundawat et al. | _arXiv_ | - | - | Knowledge Adaptation | -| [ Efficient Two-Stage Model Retraining for Machine Unlearning](https://openaccess.thecvf.com/content/CVPR2022W/HCIS/html/Kim_Efficient_Two-Stage_Model_Retraining_for_Machine_Unlearning_CVPRW_2022_paper.html) | 2022 | Kim and Woo | _CVPR Workshop_ | - | - | | -| [Learn to Forget: Machine Unlearning Via Neuron Masking](https://ieeexplore.ieee.org/abstract/document/9844865?casa_token=_eowH3BTt1sAAAAA:X0uCpLxOwcFRNJHoo3AtA0ay4t075_cSptgTMznsjusnvgySq-rJe8GC285YhWG4Q0fUmP9Sodw0) | 2021 | Ma et al. | _IEEE_ | Forsaken | - | Mask Gradients | -| [Adaptive Machine Unlearning](https://proceedings.neurips.cc/paper/2021/hash/87f7ee4fdb57bdfd52179947211b7ebb-Abstract.html) | 2021 | Gupta et al. | _NeurIPS_ | - | [[Code]](https://github.com/ChrisWaites/adaptive-machine-unlearning) | Differential Privacy | -| [Descent-to-Delete: Gradient-Based Methods for Machine Unlearning](https://proceedings.mlr.press/v132/neel21a.html) | 2021 | Neel et al. | _ALT_ | - | - | Certified Removal Mechanisms | -| [Remember What You Want to Forget: Algorithms for Machine Unlearning](https://arxiv.org/abs/2103.03279) | 2021 | Sekhari et al. | _NeurIPS_ | - | - | | -| [FedEraser: Enabling Efficient Client-Level Data Removal from Federated Learning Models](https://ieeexplore.ieee.org/abstract/document/9521274) | 2021 | Liu et al. | _IWQoS_ | FedEraser | - | | -| [Federated Unlearning](https://arxiv.org/abs/2012.13891) | 2021 | Liu et al. | _IWQoS_ | FedEraser | [[Code]](https://www.dropbox.com/s/1lhx962axovbbom/FedEraser-Code.zip?dl=0) | | -| [Machine Unlearning via Algorithmic Stability](https://proceedings.mlr.press/v134/ullah21a.html) | 2021 | Ullah et al. | _COLT_ | TV | - | Certified Removal Mechanisms | -| [EMA: Auditing Data Removal from Trained Models](https://link.springer.com/chapter/10.1007/978-3-030-87240-3_76) | 2021 | Huang et al. | _MICCAI_ | EMA | [[Code]](https://github.com/Hazelsuko07/EMA) | Certified Removal Mechanisms | -| [Knowledge-Adaptation Priors](https://proceedings.neurips.cc/paper/2021/hash/a4380923dd651c195b1631af7c829187-Abstract.html) | 2021 | Khan and Swaroop | _NeurIPS_ | K-prior | [[Code]](https://github.com/team-approx-bayes/kpriors) | Knowledge Adaptation | -| [PrIU: A Provenance-Based Approach for Incrementally Updating Regression Models](https://dl.acm.org/doi/abs/10.1145/3318464.3380571) | 2020 | Wu et al. | _NeurIPS_ | PrIU | - | Knowledge Adaptation | -| [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://arxiv.org/abs/1911.04933) | 2020 | Golatkar et al. | _CVPR_ | - | - | Certified Removal Mechanisms | -| [Learn to Forget: User-Level Memorization Elimination in Federated Learning](https://www.researchgate.net/profile/Ximeng-Liu-5/publication/340134612_Learn_to_Forget_User-Level_Memorization_Elimination_in_Federated_Learning/links/5e849e64a6fdcca789e5f955/Learn-to-Forget-User-Level-Memorization-Elimination-in-Federated-Learning.pdf) | 2020 | Liu et al. | _arXiv_ | Forsaken | - | | -| [Certified Data Removal from Machine Learning Models](https://proceedings.mlr.press/v119/guo20c.html) | 2020 | Guo et al. | _ICML_ | - | - | Certified Removal Mechanisms | -| [Class Clown: Data Redaction in Machine Unlearning at Enterprise Scale](https://arxiv.org/abs/2012.04699) | 2020 | Felps et al. | _arXiv_ | - | - | Decremental Learning | -| [A Novel Online Incremental and Decremental Learning Algorithm Based on Variable Support Vector Machine](https://link.springer.com/article/10.1007/s10586-018-1772-4) | 2019 | Chen et al. | _Cluster Computing_ | - | - | Decremental Learning | -| [Making AI Forget You: Data Deletion in Machine Learning](https://papers.nips.cc/paper/2019/hash/cb79f8fa58b91d3af6c9c991f63962d3-Abstract.html) | 2019 | Ginart et al. | _NeurIPS_ | - | - | Decremental Learning | -| [Lifelong Anomaly Detection Through Unlearning](https://dl.acm.org/doi/abs/10.1145/3319535.3363226) | 2019 | Du et al. | _CCS_ | - | - | | -| [Learning Not to Learn: Training Deep Neural Networks With Biased Data](https://openaccess.thecvf.com/content_CVPR_2019/html/Kim_Learning_Not_to_Learn_Training_Deep_Neural_Networks_With_Biased_CVPR_2019_paper.html) | 2019 | Kim et al. | _CVPR_ | - | - | | -| [Efficient Repair of Polluted Machine Learning Systems via Causal Unlearning](https://dl.acm.org/citation.cfm?id=3196517) | 2018 | Cao et al. | _ASIACCS_ | KARMA | [[Code]](https://github.com/CausalUnlearning/KARMA) | | -| [Understanding Black-box Predictions via Influence Functions](https://proceedings.mlr.press/v70/koh17a.html) | 2017 | Koh et al. | _ICML_ | - | [[Code]](https://github.com/kohpangwei/influence-release) | Certified Removal Mechanisms | -| [Towards Making Systems Forget with Machine Unlearning](https://ieeexplore.ieee.org/abstract/document/7163042) | 2015 | Cao and Yang | _S&P_ | - | | -| [Towards Making Systems Forget with Machine Unlearning](https://dl.acm.org/doi/10.1109/SP.2015.35) | 2015 | Cao et al. | _S&P_ | - | - | Statistical Query Learning | -| [Incremental and decremental training for linear classification](https://dl.acm.org/doi/10.1145/2623330.2623661) | 2014 | Tsai et al. | _KDD_ | - | [[Code]](https://www.csie.ntu.edu.tw/~cjlin/papers/ws/) | Decremental Learning | -| [Multiple Incremental Decremental Learning of Support Vector Machines](https://dl.acm.org/doi/10.5555/2984093.2984196) | 2009 | Karasuyama et al. | _NIPS_ | - | - | Decremental Learning | -| [Incremental and Decremental Learning for Linear Support Vector Machines](https://dl.acm.org/doi/10.5555/1776814.1776838) | 2007 | Romero et al. | _ICANN_ | - | - | Decremental Learning | -| [Decremental Learning Algorithms for Nonlinear Langrangian and Least Squares Support Vector Machines](https://www.semanticscholar.org/paper/Decremental-Learning-Algorithms-for-Nonlinear-and-Duan-Li/312c677f0882d0dfd60bfd77346588f52aefd10f) | 2007 | Duan et al. | _OSB_ | - | - | Decremental Learning | -| [Multicategory Incremental Proximal Support Vector Classifiers](https://link.springer.com/chapter/10.1007/978-3-540-45224-9_54) | 2003 | Tveit et al. | _KES_ | - | - | Decremental Learning | -| [Incremental and Decremental Proximal Support Vector Classification using Decay Coefficients](https://link.springer.com/chapter/10.1007/978-3-540-45228-7_42) | 2003 | Tveit et al. | _DaWak_ | - | - | Decremental Learning | -| [Incremental and Decremental Support Vector Machine Learning](https://dl.acm.org/doi/10.5555/3008751.3008808) | 2000 | Cauwenberg et al. | _NeurIPS_ | - | - | Decremental Learning | -Model-Intrinsic -| [Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearning](https://arxiv.org/abs/2302.02069) | 2023 | Zhu et al. | _WWW_ | FedLU | [[Code]](https://github.com/nju-websoft/FedLU/) | GNN-based Models | -| [One-Shot Machine Unlearning with Mnemonic Code](https://arxiv.org/abs/2306.05670) | 2023 | Yamashita | _arXiv_ | One-Shot MU | - | | -| [Inductive Graph Unlearning](https://arxiv.org/pdf/2304.03093.pdf) | 2023 | Wang et al. | _USENIX_ | GUIDE | [[Code]](https://github.com/Happy2Git/GUIDE) | GNN-based Models | -| [ERM-KTP: Knowledge-level Machine Unlearning via Knowledge Transfer](https://openaccess.thecvf.com/content/CVPR2023/papers/Lin_ERM-KTP_Knowledge-Level_Machine_Unlearning_via_Knowledge_Transfer_CVPR_2023_paper.pdf) | 2023 | Lin et al. | _CVPR_ | ERM-KTP | [[Code]](https://github.com/RUIYUN-ML/ERM-KTP) | | -| [GNNDelete: A General Strategy for Unlearning in Graph Neural Networks](https://arxiv.org/abs/2302.13406) | 2023 | Cheng et al. | _ICLR_ | GNNDELETE | [[Code]](https://github.com/mims-harvard/GNNDelete) | | -| [Unfolded Self-Reconstruction LSH: Towards Machine Unlearning in Approximate Nearest Neighbour Search](https://arxiv.org/pdf/2304.02350.pdf) | 2023 | Tan et al. | _arXiv_ | USR-LSH | [[Code]](https://anonymous.4open.science/r/ann-benchmarks-3786/README.md) | | -| [Efficiently Forgetting What You Have Learned in Graph Representation Learning via Projection](https://arxiv.org/abs/2302.08990) | 2023 | Cong and Mahdavi | _AISTATS_ | PROJECTOR | [[Code]](https://github.com/CongWeilin/Projector) | GNN-based Models | -| [Unrolling SGD: Understanding Factors Influencing Machine Unlearning](https://ieeexplore.ieee.org/abstract/document/9797378) | 2022 | Thudi et al. | _EuroS&P_ | - | [[Code]](https://github.com/cleverhans-lab/unrolling-sgd) | SGD | -| [Graph Unlearning](https://arxiv.org/abs/2103.14991) | 2022 | Chen et al. | _CCS_ | GraphEraser | [[Code]](https://github.com/MinChen00/Graph-Unlearning) | Graph Neural Networks | -| [Certified Graph Unlearning](https://arxiv.org/abs/2206.09140) | 2022 | Chien et al. | _GLFrontiers Workshop_ | - | [[Code]](https://github.com/thupchnsky/sgc_unlearn) | Graph Neural Networks | -| [Skin Deep Unlearning: Artefact and Instrument Debiasing in the Context of Melanoma Classification](https://arxiv.org/abs/2109.09818) | 2022 | Bevan and Atapour-Abarghouei | _ICML_ | - | [[Code]](https://github.com/pbevan1/Skin-Deep-Unlearning) | CNN Models | -| [Near-Optimal Task Selection for Meta-Learning with Mutual Information and Online Variational Bayesian Unlearning](https://proceedings.mlr.press/v151/chen22h.html) | 2022 | Chen et al. | _AISTATS_ | - | - | Bayensian Models | -| [Unlearning Protected User Attributes in Recommendations with Adversarial Training](https://arxiv.org/abs/2206.04500) | 2022 | Ganhor et al. | _SIGIR_ | ADV-MULTVAE | [[Code]](https://github.com/CPJKU/adv-multvae) | Autoencoder-based Model | -| [Recommendation Unlearning](https://dl.acm.org/doi/abs/10.1145/3485447.3511997) | 2022 | Chen et al. | _TheWebConf_ | RecEraser | [[Code]](https://github.com/chenchongthu/Recommendation-Unlearning) | Attention-based Model | -| [Knowledge Neurons in Pretrained Transformers](https://arxiv.org/abs/2104.08696) | 2022 | Dai et al. | _ACL_ | - | [[Code]](https://github.com/Hunter-DDM/knowledge-neurons) | Transformers -| [Memory-Based Model Editing at Scale](https://proceedings.mlr.press/v162/mitchell22a/mitchell22a.pdf) | 2022 | Mitchell et al. | _MLR_ | SERAC | [[Code]](https://sites.google.com/view/serac-editing) | DNN-based Models | -| [Forgetting Fast in Recommender Systems](https://arxiv.org/abs/2208.06875) | 2022 | Liu et al. | _arXiv_ | AltEraser | - | recommendation system | -| [Unlearning Nonlinear Graph Classifiers in the Limited Training Data Regime](https://arxiv.org/abs/2211.03216) | 2022 | Pan et al. | _arXiv_ | - | - | GNN-based Models | -| [Deep Regression Unlearning](https://arxiv.org/abs/2210.08196) | 2022 | Tarun et al. | _arXiv_ | Blindspot | - | Regression Model | -| [Quark: Controllable Text Generation with Reinforced Unlearning](https://arxiv.org/abs/2205.13636) | 2022 | Lu et al. | _arXiv_ | Quark | [[Code]](https://github.com/GXimingLu/Quark) | language models | -| [Forget-SVGD: Particle-Based Bayesian Federated Unlearning](https://ieeexplore.ieee.org/abstract/document/9820602) | 2022 | Gong et al. | _DSL Workshop_ | Forget-SVGD | - | Bayensian Models | -| [Machine Unlearning of Federated Clusters](https://arxiv.org/abs/2210.16424) | 2022 | Pan et al. | _arXiv_ | SCMA | - | Federated clustering | -| [Machine Unlearning for Image Retrieval: A Generative Scrubbing Approach](https://dl.acm.org/doi/abs/10.1145/3503161.3548378) | 2022 | Zhang et al. | _MM_ | - | - | DNN-based Models | -| [Machine Unlearning: Linear Filtration for Logit-based Classifiers](https://link.springer.com/article/10.1007/s10994-022-06178-9) | 2022 | Baumhauer et al. | _Machine Learning_ | normalizing filtration | - | Softmax classifiers | -| [Deep Unlearning via Randomized Conditionally Independent Hessians](https://openaccess.thecvf.com/content/CVPR2022/html/Mehta_Deep_Unlearning_via_Randomized_Conditionally_Independent_Hessians_CVPR_2022_paper.html) | 2022 | Mehta et al. | _CVPR_ | L-CODEC | [[Code]](https://github.com/vsingh-group/LCODEC-deep-unlearning) | DNN-based Models | -| [Challenges and Pitfalls of Bayesian Unlearning](https://arxiv.org/abs/2207.03227) | 2022 | Rawat et al. | _UPML Workshop_ | - | - | Bayesian Models | -| [Federated Unlearning via Class-Discriminative Pruning](https://arxiv.org/abs/2110.11794) | 2022 | Wang et al. | _WWW_ | - | - | CNN-Based | -| [Active forgetting via influence estimation for neural networks](https://onlinelibrary.wiley.com/doi/abs/10.1002/int.22981) | 2022 | Meng et al. | _Int. J. Intel. Systems_ | SCRUBBER | - | Neural Network | -| [Variational Bayesian unlearning](https://dl.acm.org/doi/abs/10.5555/3495724.3497068) | 2022 | Nguyen et al. | _NeurIPS_ | VI | - | Bayesian Models | -| [Revisiting Machine Learning Training Process for Enhanced Data Privacy](https://dl.acm.org/doi/abs/10.1145/3474124.3474208) | 2021 | Goyal et al. | _IC3_ | - | - | DNN-based Models | -| [Knowledge Removal in Sampling-based Bayesian Inference](https://openreview.net/forum?id=dTqOcTUOQO) | 2021 | Fu et al. | _ICLR_ | - | [[Code]](https://github.com/fshp971/mcmc-unlearning) | Bayesian Models | -| [Mixed-Privacy Forgetting in Deep Networks](https://openaccess.thecvf.com/content/CVPR2021/html/Golatkar_Mixed-Privacy_Forgetting_in_Deep_Networks_CVPR_2021_paper.html) | 2021 | Golatkar et al. | _CVPR_ | - | - | DNN-based Models | -| [HedgeCut: Maintaining Randomised Trees for Low-Latency Machine Unlearning](https://dl.acm.org/doi/abs/10.1145/3448016.3457239) | 2021 | Schelter et al. | _SIGMOD_ | HedgeCut | [[Code]](https://github.com/schelterlabs/hedgecut) | Tree-based Models | -| [A Unified PAC-Bayesian Framework for Machine Unlearning via Information Risk Minimization](https://ieeexplore.ieee.org/abstract/document/9596170) | 2021 | Jose et al. | _MLSP_ | PAC-Bayesian| - | Bayesian Models | -| [DeepObliviate: A Powerful Charm for Erasing Data Residual Memory in Deep Neural Networks](https://arxiv.org/abs/2105.06209) | 2021 | He et al. | _arXiv_ | DEEPOBLIVIATE | - | DNN-based Models | -| [Approximate Data Deletion from Machine Learning Models: Algorithms and Evaluations](https://arxiv.org/abs/2002.10077) | 2021 | Izzo et al. | _AISTATS_ | PRU | [[Code]](https://github.com/zleizzo/datadeletion) | Linear/Logistics models | -| [Bayesian Inference Forgetting](https://arxiv.org/abs/2101.06417) | 2021 | Fu et al. | _arXiv_ | BIF | [[Code]](https://github.com/fshp971/BIF) | Bayesian Models | -| [Approximate Data Deletion from Machine Learning Models](https://proceedings.mlr.press/v130/izzo21a.html) | 2021 | Izzo et al. | _AISTATS_ | PRU | [[Code]](https://github.com/zleizzo/datadeletion) | Linear Models | -| [Online Forgetting Process for Linear Regression Models](https://proceedings.mlr.press/v130/li21a.html) | 2021 | Li et al. | _AISTATS_ | FIFD-OLS | - | Linear Models | -| [RevFRF: Enabling Cross-domain Random Forest Training with Revocable Federated Learning](https://ieeexplore.ieee.org/abstract/document/9514457) | 2021 | Liu et al. | _IEEE_ | RevFRF | - | Random Forrests | -| [Coded Machine Unlearning](https://ieeexplore.ieee.org/abstract/document/9458237) | 2021 | Aldaghri et al. | _IEEE Access_ | - | - | Deep Learning Models | -| [Machine Unlearning for Random Forests](http://proceedings.mlr.press/v139/brophy21a.html) | 2021 | Brophy and Lowd | _ICML_ | DaRE RF | - | Random Forrest | -| [Bayesian Variational Federated Learning and Unlearning in Decentralized Networks](https://ieeexplore.ieee.org/abstract/document/9593225) | 2021 | Gong et al. | _SPAWC_ | - | - | Bayesian Models | -| [Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations](https://link.springer.com/chapter/10.1007/978-3-030-58526-6_23) | 2020 | Golatkar et al. | _ECCV_ | - | - | DNN-based Models | -| [Influence Functions in Deep Learning Are Fragile](https://www.semanticscholar.org/paper/Influence-Functions-in-Deep-Learning-Are-Fragile-Basu-Pope/098076a2c90e42c81b843bf339446427c2ff02ed) | 2020 | Basu et al. | _arXiv_ | - | - | DNN-based Models | -| [Deep Autoencoding Topic Model With Scalable Hybrid Bayesian Inference](https://ieeexplore.ieee.org/document/9121755) | 2020 | Zhang et al. | _IEEE_ | DATM | - | Bayesian Models | -| [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://arxiv.org/abs/1911.04933) | 2020 | Golatkar et al. | _CVPR_ | - | - | DNN-based Models | -| [Uncertainty in Neural Networks: Approximately Bayesian Ensembling](https://proceedings.mlr.press/v108/pearce20a.html) | 2020 | Pearce et al. | _AISTATS_ | - | [[Code]](https://teapearce.github.io/portfolio/github_io_1_ens/) | Bayesian Models | -| [Certified Data Removal from Machine Learning Models](https://proceedings.mlr.press/v119/guo20c.html) | 2020 | Guo et al. | _ICML_ | - | - | DNN-based Models | -| [DeltaGrad: Rapid retraining of machine learning models](https://proceedings.mlr.press/v119/wu20b.html) | 2020 | Wu et al. | _ICML_ | DeltaGrad | [[Code]](https://github.com/thuwuyinjun/DeltaGrad) | DNN-based Models | -| [Making AI Forget You: Data Deletion in Machine Learning](https://papers.nips.cc/paper/2019/hash/cb79f8fa58b91d3af6c9c991f63962d3-Abstract.html) | 2019 | Ginart et al. | _NeurIPS_ | - | - | Linear Models | -| [“Amnesia” – Towards Machine Learning Models That Can Forget User Data Very Fast](http://cidrdb.org/cidr2020/papers/p32-schelter-cidr20.pdf) | 2019 | Schelter | _AIDB Workshop_ | - | [[Code]](https://github.com/schelterlabs/projects-amnesia) | Collaborative Filtering | -| [A Novel Online Incremental and Decremental Learning Algorithm Based on Variable Support Vector Machine](https://link.springer.com/article/10.1007/s10586-018-1772-4) | 2019 | Chen et al. | _Cluster Computing_ | - | - | SVM | -| [Neural Text Degeneration With Unlikelihood Training](https://arxiv.org/abs/1908.04319) | 2019 | Welleck et al. | _arXiv_ | unlikelihood training | [[Code]](https://github.com/facebookresearch/unlikelihood_training) | DNN-based | -| [Bayesian Neural Networks with Weight Sharing Using Dirichlet Processes](https://ieeexplore.ieee.org/document/8566011) | 2018 | Roth et al. | _IEEE_ | DP | [[Code]](https://github.com/wroth8/dp-bnn) | Bayesian Models | -Data-Driven -| [Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks](https://arxiv.org/abs/2212.10717) | 2022 | Di et al. | _NeurIPS-TSRML_ | - | [[Code]](https://github.com/Jimmy-di/camouflage-poisoning) | Data Poisoning | -| [Forget Unlearning: Towards True Data Deletion in Machine Learning](https://arxiv.org/pdf/2210.08911.pdf) | 2022 | Chourasia et al. | _ICLR_ | - | - | Data Influence | -| [ARCANE: An Efficient Architecture for Exact Machine Unlearning](https://www.ijcai.org/proceedings/2022/0556.pdf) | 2022 | Yan et al. | _IJCAI_ | ARCANE | - | Data Partition | -| [PUMA: Performance Unchanged Model Augmentation for Training Data Removal](https://ojs.aaai.org/index.php/AAAI/article/view/20846) | 2022 | Wu et al. | _AAAI_ | PUMA | - | Data Influence | -| [Certifiable Unlearning Pipelines for Logistic Regression: An Experimental Study](https://www.mdpi.com/2504-4990/4/3/28) | 2022 | Mahadevan and Mathioudakis | _MAKE_ | - | [[Code]](https://version.helsinki.fi/mahadeva/unlearning-experiments) | Data Influence | -| [Zero-Shot Machine Unlearning](https://arxiv.org/abs/2201.05629) | 2022 | Chundawat et al. | _arXiv_ | - | - | Data Influence | -| [GRAPHEDITOR: An Efficient Graph Representation Learning and Unlearning Approach](https://congweilin.github.io/CongWeilin.io/files/GraphEditor.pdf) | 2022 | Cong and Mahdavi | - | GRAPHEDITOR | [[Code]](https://anonymous.4open.science/r/GraphEditor-NeurIPS22-856E/README.md) | Data Influence | -| [Fast Model Update for IoT Traffic Anomaly Detection with Machine Unlearning](https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9927728) | 2022 | Fan et al. | _IEEE IoT-J_ | ViFLa | - | Data Partition | -| [Learning to Refit for Convex Learning Problems](https://arxiv.org/abs/2111.12545) | 2021 | Zeng et al. | _arXiv_ | OPTLEARN | - | Data Influence | -| [Fast Yet Effective Machine Unlearning](https://arxiv.org/abs/2111.08947) | 2021 | Ayush et al. | _arXiv_ | - | - | Data Augmentation | -| [Learning with Selective Forgetting](https://www.ijcai.org/proceedings/2021/0137.pdf) | 2021 | Shibata et al. | _IJCAI_ | - | - | Data Augmentation | -| [SSSE: Efficiently Erasing Samples from Trained Machine Learning Models](https://openreview.net/forum?id=GRMKEx3kEo) | 2021 | Peste et al. | _NeurIPS-PRIML_ | SSSE | - | Data Influence | -| [How Does Data Augmentation Affect Privacy in Machine Learning?](https://arxiv.org/abs/2007.10567) | 2021 | Yu et al. | _AAAI_ | - | [[Code]](https://github.com/dayu11/MI_with_DA) | Data Augmentation | -| [Coded Machine Unlearning](https://ieeexplore.ieee.org/document/9458237) | 2021 | Aldaghri et al. | _IEEE_ | - | - | Data Partitioning | -| [Machine Unlearning](https://ieeexplore.ieee.org/document/9519428) | 2021 | Bourtoule et al. | _IEEE_ | SISA | [[Code]](https://github.com/cleverhans-lab/machine-unlearning) | Data Partitioning | -| [How Does Data Augmentation Affect Privacy in Machine Learning?](https://ojs.aaai.org/index.php/AAAI/article/view/17284/) | 2021 | Yu et al. | _AAAI_ | - | [[Code]](https://github.com/dayu11/MI_with_DA) | Data Augmentation | -| [Amnesiac Machine Learning](https://ojs.aaai.org/index.php/AAAI/article/view/17371) | 2021 | Graves et al. | _AAAI_ | AmnesiacML | [[Code]](https://github.com/lmgraves/AmnesiacML) | Data Influence | -| [Unlearnable Examples: Making Personal Data Unexploitable](https://arxiv.org/abs/2101.04898) | 2021 | Huang et al. | _ICLR_ | - | [[Code]](https://github.com/HanxunH/Unlearnable-Examples) | Data Augmentation | -| [Descent-to-Delete: Gradient-Based Methods for Machine Unlearning](https://proceedings.mlr.press/v132/neel21a.html) | 2021 | Neel et al. | _ALT_ | - | - | Data Influence | -| [Fawkes: Protecting Privacy against Unauthorized Deep Learning Models](https://dl.acm.org/doi/abs/10.5555/3489212.3489302) | 2020 | Shan et al. | _USENIX Sec. Sym._ | Fawkes | [[Code]](https://github.com/Shawn-Shan/fawkes) | Data Augmentation | -| [PrIU: A Provenance-Based Approach for Incrementally Updating Regression Models](https://dl.acm.org/doi/abs/10.1145/3318464.3380571) | 2020 | Wu et al. | _SIGMOD_ | PrIU/PrIU-opt | - | Data Influence | -| [DeltaGrad: Rapid retraining of machine learning models](https://proceedings.mlr.press/v119/wu20b.html) | 2020 | Wu et al. | _ICML_ | DeltaGrad | [[Code]](https://github.com/thuwuyinjun/DeltaGrad) | Data Influence | \ No newline at end of file +| [Please Tell Me More: Privacy Impact of Explainability through the Lens of Membership Inference Attack](https://www.computer.org/csdl/proceedings-article/sp/2024/313000a120/1Ub23teQ7PG) | 2024 | _SP_ | Feature-based | Membership Inference | Differential Privacy, Privacy-Preserving Models, DP-SGD | - | +| [On the Privacy Risks of Algorithmic Recourse](https://proceedings.mlr.press/v206/pawelczyk23a.html) | 2023 | _AISTATS_ | Counterfactual | Membership Inference | Differential Privacy | - | +| [The Privacy Issue of Counterfactual Explanations: Explanation Linkage Attacks](https://dl.acm.org/doi/full/10.1145/3608482) | 2023 | _TIST_ | Counterfactual | Linkage | Anonymisaion | - | +| [Feature-based Learning for Diverse and Privacy-Preserving Counterfactual Explanations](https://dl.acm.org/doi/abs/10.1145/3580305.3599343) | 2023 | _KDD_ | Counterfactual | - | Perturbation | [[Code]](https://github.com/isVy08/L2C/) | +| [Private Graph Extraction via Feature Explanations](https://petsymposium.org/popets/2023/popets-2023-0041.pdf) | 2023 | _PETS_ | Feature-based | Graph Extraction | Perturbation | [[Code]](https://github.com/iyempissy/graph-stealing-attacks-with-explanation) | +| [Privacy-Preserving Algorithmic Recourse](https://arxiv.org/abs/2311.14137) | 2023 | _ICAIF_ | Counterfactual | - | Differential Privacy | - | +| [Accurate, Explainable, and Private Models: Providing Recourse While Minimizing Training Data Leakage](https://arxiv.org/abs/2308.04341) | 2023 | _ICML-Workshop_ | Counterfactual | Membership Inference | Differential Privacy | - | +| [Probabilistic Dataset Reconstruction from Interpretable Models](https://arxiv.org/abs/2308.15099) | 2023 | _arXiv_ | Interpretable Surrogates | Data Reconstruction | - | [[Code]](https://github.com/ferryjul/ProbabilisticDatasetsReconstruction) | +| [DeepFixCX: Explainable privacy-preserving image compression for medical image analysis](https://wires.onlinelibrary.wiley.com/doi/full/10.1002/widm.1495) | 2023 | _WIREs-DMKD_ | Case-based | Identity recognition | Anonymisation | [[Code]](https://github.com/adgaudio/DeepFixCX) | +| [XorSHAP: Privacy-Preserving Explainable AI for Decision Tree Models](https://eprint.iacr.org/2023/1859) | 2023 | _Preprint_ | Shapley | - | Multi-party Computation | - | +| DP-XAI | 2023 | _Github_ | ALE plot | - | Differential Privacy | [[Code]](https://github.com/lange-martin/dp-global-xai) | +| [Inferring Sensitive Attributes from Model Explanations](https://dl.acm.org/doi/abs/10.1145/3511808.3557362) | 2022 | _CIKM_ | Gradient-based, Perturbation-based | Attribute Inference | - | [[Code]](https://github.com/vasishtduddu/AttInfExplanations) | +| [Model explanations with differential privacy](https://dl.acm.org/doi/abs/10.1145/3531146.3533235) | 2022 | _FAccT_ | Feature-based | - | Differential Privacy | - | +| [DualCF: Efficient Model Extraction Attack from Counterfactual Explanations](https://dl.acm.org/doi/10.1145/3531146.3533188) | 2022 | _FAccT_ | Counterfactual | Model Extraction | - | - | +| [Feature Inference Attack on Shapley Values](https://dl.acm.org/doi/abs/10.1145/3548606.3560573) | 2022 | _CCS_ | Shapley | Attribute/Feature Inference | Low-dimensional | - | +| [Evaluating the privacy exposure of interpretable global explainers](https://ieeexplore.ieee.org/abstract/document/10063510/), [Privacy Risk of Global Explainers](https://ebooks.iospress.nl/doi/10.3233/FAIA220206) | 2022 | _CogMI_ | Interpretable Surrogates | Membership Inference | - | - | +| [Privacy-Preserving Case-Based Explanations: Enabling Visual Interpretability by Protecting Privacy](https://ieeexplore.ieee.org/document/9729808/) | 2022 | _IEEE Access_ | Example-based | - | Anonymisation | - | +| [On the amplification of security and privacy risks by post-hoc explanations in machine learning models](https://arxiv.org/abs/2206.14004) | 2022 | _arXiv_ | Feature-based | Membership Inference | - | - | +| [Differentially Private Counterfactuals via Functional Mechanism](https://arxiv.org/abs/2208.02878) | 2022 | _arXiv_ | Counterfactual | - | Differential Privacy | - | +| [Differentially Private Shapley Values for Data Evaluation](https://arxiv.org/abs/2206.00511) | 2022 | _arXiv_ | Shapley | - | Differential Privacy | [[Code]](https://github.com/amiratag/DataShapley) | +| [Exploiting Explanations for Model Inversion Attacks](https://openaccess.thecvf.com/content/ICCV2021/html/Zhao_Exploiting_Explanations_for_Model_Inversion_Attacks_ICCV_2021_paper.html) | 2021 | _ICCV_ | Gradient-based, Interpretable Surrogates | Model Inversion | - | - | +| [On the Privacy Risks of Model Explanations](https://dl.acm.org/doi/abs/10.1145/3461702.3462533) | 2021 | AIES | Feature-based, Shapley, Counterfactual | Membership Inference | - | - | +| [Adversarial XAI Methods in Cybersecurity](https://ieeexplore.ieee.org/abstract/document/9555622) | 2021 | TIFS | Counterfactual | Membership Inference | - | - | +| [MEGEX: Data-Free Model Extraction Attack against Gradient-Based Explainable AI](https://arxiv.org/abs/2107.08909) | 2021 | _arXiv_ | Gradient-based | Model Extraction | - | [[Code]](https://github.com/cake-lab/datafree-model-extraction) | +| [Robust Counterfactual Explanations for Privacy-Preserving SVM](https://www.diva-portal.org/smash/record.jsf?pid=diva2%3A1581005&dswid=5229), [Robust Explanations for Private Support Vector Machines](https://arxiv.org/abs/2102.03785) | 2021 | _ICML-Workshop_ | Counterfactual | - | Private SVM | [[Code]](https://github.com/rami-mochaourab/robust-explanation-SVM) | +| [When Differential Privacy Meets Interpretability: A Case Study](https://arxiv.org/abs/2106.13203) | 2021 | _RCV-CVPR_ | Interpretable Models | - | Differential Privacy | - | +| [Differentially Private Quantiles](https://proceedings.mlr.press/v139/gillenwater21a.html) | 2021 | _ICML_ | Quantiles | - | Differential Privacy | [[Code]](https://github.com/google-research/google-research/tree/master/dp_multiq) | +| [FOX: Fooling with Explanations : Privacy Protection with Adversarial Reactions in Social Media](https://ieeexplore.ieee.org/document/9647778) | 2021 | _PST_ | - | Attribute Inference | Privacy-Protecting Explanation | - | +| [Privacy-preserving generative adversarial network for case-based explainability in medical image analysis](https://ieeexplore.ieee.org/abstract/document/9598877/) | 2021 | _IEEE Access_ | Example-based | - | Generative Anonymisation | - | +| [Interpretable and Differentially Private Predictions](https://ojs.aaai.org/index.php/AAAI/article/view/5827) | 2020 | _AAAI_ | Locally linear maps | - | Differential Privacy | [[Code]](https://github.com/frhrdr/dp-llm) | +| [Model extraction from counterfactual explanations](https://arxiv.org/abs/2009.01884) | 2020 | _arXiv_ | Counterfactual | Model Extraction | - | [[Code]](https://github.com/aivodji/mrce) | +| [Model Reconstruction from Model Explanations](https://dl.acm.org/doi/10.1145/3287560.3287562) | 2019 | _FAT*_ | Gradient-based | Model Reconstruction, Model Extraction | - | - | +| [Interpret Federated Learning with Shapley Values](https://arxiv.org/abs/1905.04519) | 2019 | __ | Shapley | - | Federated | [[Code]](https://github.com/crownpku/federated_shap) | +| [Collaborative Explanation of Deep Models with Limited Interaction for Trade Secret and Privacy Preservation](https://dl.acm.org/doi/10.1145/3308560.3317586) | 2019 | _WWW_ | Feature-based | - | Collaborative rule-based model | - | +| [Model inversion attacks that exploit confidence information and basic countermeasures](https://dl.acm.org/doi/abs/10.1145/2810103.2813677) | 2015 | _CCS_ | Confidence scores | Reconstruction, Model Inversion | - | - | \ No newline at end of file diff --git a/script/output.txt b/script/output.txt index ca8f93f..9e9394e 100644 --- a/script/output.txt +++ b/script/output.txt @@ -1,969 +1,317 @@ - - - Towards Adversarial Evaluations for Inexact Machine Unlearning - arXiv - 2023 - [Code] - Model-Agnostic - - - KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment - arXiv - 2023 - [Code] - Model-Agnostic - - - On the Trade-Off between Actionable Explanations and the Right to be Forgotten - arXiv - 2023 - - - Model-Agnostic - - - Towards Unbounded Machine Unlearning - arXiv - 2023 - [Code] - Model-Agnostic - - - Netflix and Forget: Efficient and Exact Machine Unlearning from Bi-linear Recommendations - arXiv - 2023 - - - Model-Agnostic - - - To Be Forgotten or To Be Fair: Unveiling Fairness Implications of Machine Unlearning Methods - arXiv - 2023 - [Code] - Model-Agnostic - - - Sequential Informed Federated Unlearning: Efficient and Provable Client Unlearning in Federated Optimization - arXiv - 2022 - - - Model-Agnostic - - - Certified Data Removal in Sum-Product Networks - ICKG - 2022 - [Code] - Model-Agnostic - - - Learning with Recoverable Forgetting - ECCV - 2022 - - - Model-Agnostic - - - Continual Learning and Private Unlearning - CoLLAs - 2022 - [Code] - Model-Agnostic - - - Verifiable and Provably Secure Machine Unlearning - arXiv - 2022 - [Code] - Model-Agnostic - - - VeriFi: Towards Verifiable Federated Unlearning - arXiv - 2022 - - - Model-Agnostic - - - FedRecover: Recovering from Poisoning Attacks in Federated Learning using Historical Information - S&P - 2022 - - - Model-Agnostic - - - Fast Yet Effective Machine Unlearning - arXiv - 2022 - - - Model-Agnostic - - - Membership Inference via Backdooring - IJCAI - 2022 - [Code] - Model-Agnostic - - - Forget Unlearning: Towards True Data-Deletion in Machine Learning - ICLR - 2022 - - - Model-Agnostic - - - Zero-Shot Machine Unlearning - arXiv - 2022 - - - Model-Agnostic - - - Efficient Attribute Unlearning: Towards Selective Removal of Input Attributes from Feature Representations - arXiv - 2022 - - - Model-Agnostic - - - Few-Shot Unlearning - ICLR - 2022 - - - Model-Agnostic - - - Federated Unlearning: How to Efficiently Erase a Client in FL? - UpML Workshop - 2022 - - - Model-Agnostic - - - Machine Unlearning Method Based On Projection Residual - DSAA - 2022 - - - Model-Agnostic - - - Hard to Forget: Poisoning Attacks on Certified Machine Unlearning - AAAI - 2022 - [Code] - Model-Agnostic - - - Athena: Probabilistic Verification of Machine Unlearning - PoPETs - 2022 - - - Model-Agnostic - - - FP2-MIA: A Membership Inference Attack Free of Posterior Probability in Machine Unlearning - ProvSec - 2022 - - - Model-Agnostic - - - Deletion Inference, Reconstruction, and Compliance in Machine (Un)Learning - PETS - 2022 - - - Model-Agnostic - - - Prompt Certified Machine Unlearning with Randomized Gradient Smoothing and Quantization - NeurIPS - 2022 - - - Model-Agnostic - - - The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining - INFOCOM - 2022 - [Code] - Model-Agnostic - - - Backdoor Defense with Machine Unlearning - INFOCOM - 2022 - - - Model-Agnostic - - - Markov Chain Monte Carlo-Based Machine Unlearning: Unlearning What Needs to be Forgotten - ASIA CCS - 2022 - - - Model-Agnostic - - - Federated Unlearning for On-Device Recommendation - arXiv - 2022 - - - Model-Agnostic - - - Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher - arXiv - 2022 - - - Model-Agnostic - - - Efficient Two-Stage Model Retraining for Machine Unlearning - CVPR Workshop - 2022 - - - Model-Agnostic - - - Learn to Forget: Machine Unlearning Via Neuron Masking - IEEE - 2021 - - - Model-Agnostic - - - Adaptive Machine Unlearning - NeurIPS - 2021 - [Code] - Model-Agnostic - - - Descent-to-Delete: Gradient-Based Methods for Machine Unlearning - ALT - 2021 - - - Model-Agnostic - - - Remember What You Want to Forget: Algorithms for Machine Unlearning - NeurIPS - 2021 - - - Model-Agnostic - - - FedEraser: Enabling Efficient Client-Level Data Removal from Federated Learning Models - IWQoS - 2021 - - - Model-Agnostic - - - Federated Unlearning - IWQoS - 2021 - [Code] - Model-Agnostic - - - Machine Unlearning via Algorithmic Stability - COLT - 2021 - - - Model-Agnostic - - - EMA: Auditing Data Removal from Trained Models - MICCAI - 2021 - [Code] - Model-Agnostic - - - Knowledge-Adaptation Priors - NeurIPS - 2021 - [Code] - Model-Agnostic - - - PrIU: A Provenance-Based Approach for Incrementally Updating Regression Models - NeurIPS - 2020 - - - Model-Agnostic - - - Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks - CVPR - 2020 - - - Model-Agnostic - - - Learn to Forget: User-Level Memorization Elimination in Federated Learning - arXiv - 2020 - - - Model-Agnostic - - - Certified Data Removal from Machine Learning Models - ICML - 2020 - - - Model-Agnostic - - - Class Clown: Data Redaction in Machine Unlearning at Enterprise Scale - arXiv - 2020 - - - Model-Agnostic - - - A Novel Online Incremental and Decremental Learning Algorithm Based on Variable Support Vector Machine - Cluster Computing - 2019 - - - Model-Agnostic - - - Making AI Forget You: Data Deletion in Machine Learning - NeurIPS - 2019 - - - Model-Agnostic - - - Lifelong Anomaly Detection Through Unlearning - CCS - 2019 - - - Model-Agnostic - - - Learning Not to Learn: Training Deep Neural Networks With Biased Data - CVPR - 2019 - - - Model-Agnostic - - - Efficient Repair of Polluted Machine Learning Systems via Causal Unlearning - ASIACCS - 2018 - [Code] - Model-Agnostic - - - Understanding Black-box Predictions via Influence Functions - ICML - 2017 - [Code] - Model-Agnostic - - - Towards Making Systems Forget with Machine Unlearning - S&P - 2015 - - - Model-Agnostic - - - Towards Making Systems Forget with Machine Unlearning - S&P - 2015 - - - Model-Agnostic - - - Incremental and decremental training for linear classification - KDD - 2014 - [Code] - Model-Agnostic - - - Multiple Incremental Decremental Learning of Support Vector Machines - NIPS - 2009 - - - Model-Agnostic - - - Incremental and Decremental Learning for Linear Support Vector Machines - ICANN - 2007 - - - Model-Agnostic - - - Decremental Learning Algorithms for Nonlinear Langrangian and Least Squares Support Vector Machines - OSB - 2007 - - - Model-Agnostic - - - Multicategory Incremental Proximal Support Vector Classifiers - KES - 2003 - - - Model-Agnostic - - - Incremental and Decremental Proximal Support Vector Classification using Decay Coefficients - DaWak - 2003 - - - Model-Agnostic - - - Incremental and Decremental Support Vector Machine Learning - NeurIPS - 2000 - - - Model-Agnostic - - - - Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearning - WWW - 2023 - [Code] - Model-Intrinsic - - - One-Shot Machine Unlearning with Mnemonic Code - arXiv - 2023 - - - Model-Intrinsic - - - Inductive Graph Unlearning - USENIX - 2023 - [Code] - Model-Intrinsic - - - ERM-KTP: Knowledge-level Machine Unlearning via Knowledge Transfer - CVPR - 2023 - [Code] - Model-Intrinsic - - - GNNDelete: A General Strategy for Unlearning in Graph Neural Networks - ICLR - 2023 - [Code] - Model-Intrinsic - - - Unfolded Self-Reconstruction LSH: Towards Machine Unlearning in Approximate Nearest Neighbour Search - arXiv - 2023 - [Code] - Model-Intrinsic - - - Efficiently Forgetting What You Have Learned in Graph Representation Learning via Projection - AISTATS - 2023 - [Code] - Model-Intrinsic - - - Unrolling SGD: Understanding Factors Influencing Machine Unlearning - EuroS&P - 2022 - [Code] - Model-Intrinsic - - - Graph Unlearning - CCS - 2022 - [Code] - Model-Intrinsic - - - Certified Graph Unlearning - GLFrontiers Workshop - 2022 - [Code] - Model-Intrinsic - - - Skin Deep Unlearning: Artefact and Instrument Debiasing in the Context of Melanoma Classification - ICML - 2022 - [Code] - Model-Intrinsic - - - Near-Optimal Task Selection for Meta-Learning with Mutual Information and Online Variational Bayesian Unlearning - AISTATS - 2022 - - - Model-Intrinsic - - - Unlearning Protected User Attributes in Recommendations with Adversarial Training - SIGIR - 2022 - [Code] - Model-Intrinsic - - - Recommendation Unlearning - TheWebConf - 2022 - [Code] - Model-Intrinsic - - - Knowledge Neurons in Pretrained Transformers - ACL - 2022 - [Code] - Model-Intrinsic - - - Memory-Based Model Editing at Scale - MLR - 2022 - [Code] - Model-Intrinsic - - - Forgetting Fast in Recommender Systems - arXiv - 2022 - - - Model-Intrinsic - - - Unlearning Nonlinear Graph Classifiers in the Limited Training Data Regime - arXiv - 2022 - - - Model-Intrinsic - - - Deep Regression Unlearning - arXiv - 2022 - - - Model-Intrinsic - - - Quark: Controllable Text Generation with Reinforced Unlearning - arXiv - 2022 - [Code] - Model-Intrinsic - - - Forget-SVGD: Particle-Based Bayesian Federated Unlearning - DSL Workshop - 2022 - - - Model-Intrinsic - - - Machine Unlearning of Federated Clusters - arXiv - 2022 - - - Model-Intrinsic - - - Machine Unlearning for Image Retrieval: A Generative Scrubbing Approach - MM - 2022 - - - Model-Intrinsic - - - Machine Unlearning: Linear Filtration for Logit-based Classifiers - Machine Learning - 2022 - - - Model-Intrinsic - - - Deep Unlearning via Randomized Conditionally Independent Hessians - CVPR - 2022 - [Code] - Model-Intrinsic - - - Challenges and Pitfalls of Bayesian Unlearning - UPML Workshop - 2022 - - - Model-Intrinsic - - - Federated Unlearning via Class-Discriminative Pruning - WWW - 2022 - - - Model-Intrinsic - - - Active forgetting via influence estimation for neural networks - Int. J. Intel. Systems - 2022 - - - Model-Intrinsic - - - Variational Bayesian unlearning - NeurIPS - 2022 - - - Model-Intrinsic - - - Revisiting Machine Learning Training Process for Enhanced Data Privacy - IC3 - 2021 - - - Model-Intrinsic - - - Knowledge Removal in Sampling-based Bayesian Inference - ICLR - 2021 - [Code] - Model-Intrinsic - - - Mixed-Privacy Forgetting in Deep Networks - CVPR - 2021 - - - Model-Intrinsic - - - HedgeCut: Maintaining Randomised Trees for Low-Latency Machine Unlearning - SIGMOD - 2021 - [Code] - Model-Intrinsic - - - A Unified PAC-Bayesian Framework for Machine Unlearning via Information Risk Minimization - MLSP - 2021 - - - Model-Intrinsic - - - DeepObliviate: A Powerful Charm for Erasing Data Residual Memory in Deep Neural Networks - arXiv - 2021 - - - Model-Intrinsic - - - Approximate Data Deletion from Machine Learning Models: Algorithms and Evaluations - AISTATS - 2021 - [Code] - Model-Intrinsic - - - Bayesian Inference Forgetting - arXiv - 2021 - [Code] - Model-Intrinsic - - - Approximate Data Deletion from Machine Learning Models - AISTATS - 2021 - [Code] - Model-Intrinsic - - - Online Forgetting Process for Linear Regression Models - AISTATS - 2021 - - - Model-Intrinsic - - - RevFRF: Enabling Cross-domain Random Forest Training with Revocable Federated Learning - IEEE - 2021 - - - Model-Intrinsic - - - Coded Machine Unlearning - IEEE Access - 2021 - - - Model-Intrinsic - - - Machine Unlearning for Random Forests - ICML - 2021 - - - Model-Intrinsic - - - Bayesian Variational Federated Learning and Unlearning in Decentralized Networks - SPAWC - 2021 - - - Model-Intrinsic - - - Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations - ECCV - 2020 - - - Model-Intrinsic - - - Influence Functions in Deep Learning Are Fragile - arXiv - 2020 - - - Model-Intrinsic - - - Deep Autoencoding Topic Model With Scalable Hybrid Bayesian Inference - IEEE - 2020 - - - Model-Intrinsic - - - Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks - CVPR - 2020 - - - Model-Intrinsic - - - Uncertainty in Neural Networks: Approximately Bayesian Ensembling - AISTATS - 2020 - [Code] - Model-Intrinsic - - - Certified Data Removal from Machine Learning Models - ICML - 2020 - - - Model-Intrinsic - - - DeltaGrad: Rapid retraining of machine learning models - ICML - 2020 - [Code] - Model-Intrinsic - - - Making AI Forget You: Data Deletion in Machine Learning - NeurIPS - 2019 - - - Model-Intrinsic - - - “Amnesia” – Towards Machine Learning Models That Can Forget User Data Very Fast - AIDB Workshop - 2019 - [Code] - Model-Intrinsic - - - A Novel Online Incremental and Decremental Learning Algorithm Based on Variable Support Vector Machine - Cluster Computing - 2019 - - - Model-Intrinsic - - - Neural Text Degeneration With Unlikelihood Training - arXiv - 2019 - [Code] - Model-Intrinsic - - - Bayesian Neural Networks with Weight Sharing Using Dirichlet Processes - IEEE - 2018 - [Code] - Model-Intrinsic - - - - Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks - NeurIPS-TSRML - 2022 - [Code] - Data-Driven - - - Forget Unlearning: Towards True Data Deletion in Machine Learning - ICLR - 2022 - - - Data-Driven - - - ARCANE: An Efficient Architecture for Exact Machine Unlearning - IJCAI - 2022 - - - Data-Driven - - - PUMA: Performance Unchanged Model Augmentation for Training Data Removal - AAAI - 2022 - - - Data-Driven - - - Certifiable Unlearning Pipelines for Logistic Regression: An Experimental Study - MAKE - 2022 - [Code] - Data-Driven - - - Zero-Shot Machine Unlearning - arXiv - 2022 - - - Data-Driven - - - GRAPHEDITOR: An Efficient Graph Representation Learning and Unlearning Approach - - - 2022 - [Code] - Data-Driven - - - Fast Model Update for IoT Traffic Anomaly Detection with Machine Unlearning - IEEE IoT-J - 2022 - - - Data-Driven - - - Learning to Refit for Convex Learning Problems - arXiv - 2021 - - - Data-Driven - - - Fast Yet Effective Machine Unlearning - arXiv - 2021 - - - Data-Driven - - - Learning with Selective Forgetting - IJCAI - 2021 - - - Data-Driven - - - SSSE: Efficiently Erasing Samples from Trained Machine Learning Models - NeurIPS-PRIML - 2021 - - - Data-Driven - - - How Does Data Augmentation Affect Privacy in Machine Learning? - AAAI - 2021 - [Code] - Data-Driven - - - Coded Machine Unlearning - IEEE - 2021 - - - Data-Driven - - - Machine Unlearning - IEEE - 2021 - [Code] - Data-Driven - - - How Does Data Augmentation Affect Privacy in Machine Learning? - AAAI - 2021 - [Code] - Data-Driven - - - Amnesiac Machine Learning - AAAI - 2021 - [Code] - Data-Driven - - - Unlearnable Examples: Making Personal Data Unexploitable - ICLR - 2021 - [Code] - Data-Driven - - - Descent-to-Delete: Gradient-Based Methods for Machine Unlearning - ALT - 2021 - - - Data-Driven - - - Fawkes: Protecting Privacy against Unauthorized Deep Learning Models - USENIX Sec. Sym. - 2020 - [Code] - Data-Driven - - - PrIU: A Provenance-Based Approach for Incrementally Updating Regression Models - SIGMOD - 2020 - - - Data-Driven - - - DeltaGrad: Rapid retraining of machine learning models - ICML - 2020 - [Code] - Data-Driven - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Please Tell Me More: Privacy Impact of Explainability through the Lens of Membership Inference Attack2024SPFeature-basedMembership InferenceDifferential Privacy, Privacy-Preserving Models, DP-SGD-
On the Privacy Risks of Algorithmic Recourse2023AISTATSCounterfactualMembership InferenceDifferential Privacy-
The Privacy Issue of Counterfactual Explanations: Explanation Linkage Attacks2023TISTCounterfactualLinkageAnonymisaion-
Feature-based Learning for Diverse and Privacy-Preserving Counterfactual Explanations2023KDDCounterfactual-Perturbation[Code]
Private Graph Extraction via Feature Explanations2023PETSFeature-basedGraph ExtractionPerturbation[Code]
Privacy-Preserving Algorithmic Recourse2023ICAIFCounterfactual-Differential Privacy-
Accurate, Explainable, and Private Models: Providing Recourse While Minimizing Training Data Leakage2023ICML-WorkshopCounterfactualMembership InferenceDifferential Privacy-
Probabilistic Dataset Reconstruction from Interpretable Models2023arXivInterpretable SurrogatesData Reconstruction-[Code]
DeepFixCX: Explainable privacy-preserving image compression for medical image analysis2023WIREs-DMKDCase-basedIdentity recognitionAnonymisation[Code]
XorSHAP: Privacy-Preserving Explainable AI for Decision Tree Models2023PreprintShapley-Multi-party Computation-
-2023GithubALE plot-Differential Privacy[Code]
Inferring Sensitive Attributes from Model Explanations2022CIKMGradient-based, Perturbation-basedAttribute Inference-[Code]
Model explanations with differential privacy2022FAccTFeature-based-Differential Privacy-
DualCF: Efficient Model Extraction Attack from Counterfactual Explanations2022FAccTCounterfactualModel Extraction--
Feature Inference Attack on Shapley Values2022CCSShapleyAttribute/Feature InferenceLow-dimensional-
Evaluating the privacy exposure of interpretable global explainers2022CogMIInterpretable SurrogatesMembership Inference--
Privacy-Preserving Case-Based Explanations: Enabling Visual Interpretability by Protecting Privacy2022IEEE AccessExample-based-Anonymisation-
On the amplification of security and privacy risks by post-hoc explanations in machine learning models2022arXivFeature-basedMembership Inference--
Differentially Private Counterfactuals via Functional Mechanism2022arXivCounterfactual-Differential Privacy-
Differentially Private Shapley Values for Data Evaluation2022arXivShapley-Differential Privacy[Code]
Exploiting Explanations for Model Inversion Attacks2021ICCVGradient-based, Interpretable SurrogatesModel Inversion--
On the Privacy Risks of Model Explanations2021AIESFeature-based, Shapley, CounterfactualMembership Inference--
Adversarial XAI Methods in Cybersecurity2021TIFSCounterfactualMembership Inference--
MEGEX: Data-Free Model Extraction Attack against Gradient-Based Explainable AI2021arXivGradient-basedModel Extraction-[Code]
Robust Counterfactual Explanations for Privacy-Preserving SVM2021ICML-WorkshopCounterfactual-Private SVM[Code]
When Differential Privacy Meets Interpretability: A Case Study2021RCV-CVPRInterpretable Models-Differential Privacy-
Differentially Private Quantiles2021ICMLQuantiles-Differential Privacy[Code]
FOX: Fooling with Explanations : Privacy Protection with Adversarial Reactions in Social Media2021PST-Attribute InferencePrivacy-Protecting Explanation-
Privacy-preserving generative adversarial network for case-based explainability in medical image analysis2021IEEE AccessExample-based-Generative Anonymisation-
Interpretable and Differentially Private Predictions2020AAAILocally linear maps-Differential Privacy[Code]
Model extraction from counterfactual explanations2020arXivCounterfactualModel Extraction-[Code]
Model Reconstruction from Model Explanations2019FAT*Gradient-basedModel Reconstruction, Model Extraction--
Interpret Federated Learning with Shapley Values2019-Shapley-Federated[Code]
Collaborative Explanation of Deep Models with Limited Interaction for Trade Secret and Privacy Preservation2019WWWFeature-based-Collaborative rule-based model-
Model inversion attacks that exploit confidence information and basic countermeasures2015CCSConfidence scoresReconstruction, Model Inversion--
\ No newline at end of file diff --git a/script/translator.ipynb b/script/translator.ipynb index 4b8df9b..8437165 100644 --- a/script/translator.ipynb +++ b/script/translator.ipynb @@ -36,1044 +36,63 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 7, "id": "84f9273a", "metadata": { "scrolled": false }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "----\n", - "Towards Adversarial Evaluations for Inexact Machine Unlearning\n", - "https://arxiv.org/abs/2201.06640\n", - "arXiv\n", - "2023\n", - "https://github.com/shash42/Evaluating-Inexact-Unlearning\n", - "Model-Agnostic\n", - "----\n", - "KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment\n", - "https://arxiv.org/abs/2305.06535\n", - "arXiv\n", - "2023\n", - "https://github.com/Lingzhi-WANG/KGAUnlearn\n", - "Model-Agnostic\n", - "----\n", - "On the Trade-Off between Actionable Explanations and the Right to be Forgotten\n", - "https://openreview.net/pdf?id=HWt4BBZjVW\n", - "arXiv\n", - "2023\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Towards Unbounded Machine Unlearning\n", - "https://arxiv.org/pdf/2302.09880\n", - "arXiv\n", - "2023\n", - "https://github.com/Meghdad92/SCRUB\n", - "Model-Agnostic\n", - "----\n", - "Netflix and Forget: Efficient and Exact Machine Unlearning from Bi-linear Recommendations\n", - "https://arxiv.org/abs/2302.06676\n", - "arXiv\n", - "2023\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "To Be Forgotten or To Be Fair: Unveiling Fairness Implications of Machine Unlearning Methods\n", - "https://arxiv.org/abs/2302.03350\n", - "arXiv\n", - "2023\n", - "https://github.com/cleverhans-lab/machine-unlearning\n", - "Model-Agnostic\n", - "----\n", - "Sequential Informed Federated Unlearning: Efficient and Provable Client Unlearning in Federated Optimization\n", - "https://arxiv.org/abs/2211.11656\n", - "arXiv\n", - "2022\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Certified Data Removal in Sum-Product Networks\n", - "https://arxiv.org/abs/2210.01451\n", - "ICKG\n", - "2022\n", - "https://github.com/ROYALBEFF/UnlearnSPN\n", - "Model-Agnostic\n", - "----\n", - "Learning with Recoverable Forgetting\n", - "https://arxiv.org/abs/2207.08224\n", - "ECCV\n", - "2022\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Continual Learning and Private Unlearning\n", - "https://arxiv.org/abs/2203.12817\n", - "CoLLAs\n", - "2022\n", - "https://github.com/Cranial-XIX/Continual-Learning-Private-Unlearning\n", - "Model-Agnostic\n", - "----\n", - "Verifiable and Provably Secure Machine Unlearning\n", - "https://arxiv.org/abs/2210.09126\n", - "arXiv\n", - "2022\n", - "https://github.com/cleverhans-lab/verifiable-unlearning\n", - "Model-Agnostic\n", - "----\n", - "VeriFi: Towards Verifiable Federated Unlearning\n", - "https://arxiv.org/abs/2205.12709\n", - "arXiv\n", - "2022\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "FedRecover: Recovering from Poisoning Attacks in Federated Learning using Historical Information\n", - "https://arxiv.org/abs/2210.10936\n", - "S&P\n", - "2022\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Fast Yet Effective Machine Unlearning\n", - "https://arxiv.org/abs/2111.08947\n", - "arXiv\n", - "2022\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Membership Inference via Backdooring\n", - "https://arxiv.org/abs/2206.04823\n", - "IJCAI\n", - "2022\n", - "https://github.com/HongshengHu/membership-inference-via-backdooring\n", - "Model-Agnostic\n", - "----\n", - "Forget Unlearning: Towards True Data-Deletion in Machine Learning\n", - "https://arxiv.org/abs/2210.08911\n", - "ICLR\n", - "2022\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Zero-Shot Machine Unlearning\n", - "https://arxiv.org/abs/2201.05629\n", - "arXiv\n", - "2022\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Efficient Attribute Unlearning: Towards Selective Removal of Input Attributes from Feature Representations\n", - "https://arxiv.org/abs/2202.13295\n", - "arXiv\n", - "2022\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Few-Shot Unlearning\n", - "https://download.huan-zhang.com/events/srml2022/accepted/yoon22fewshot.pdf\n", - "ICLR\n", - "2022\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Federated Unlearning: How to Efficiently Erase a Client in FL?\n", - "https://arxiv.org/abs/2207.05521\n", - "UpML Workshop\n", - "2022\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Machine Unlearning Method Based On Projection Residual\n", - "https://arxiv.org/abs/2209.15276\n", - "DSAA\n", - "2022\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Hard to Forget: Poisoning Attacks on Certified Machine Unlearning\n", - "https://ojs.aaai.org/index.php/AAAI/article/view/20736\n", - "AAAI\n", - "2022\n", - "https://github.com/ngmarchant/attack-unlearning\n", - "Model-Agnostic\n", - "----\n", - "Athena: Probabilistic Verification of Machine Unlearning\n", - "https://web.archive.org/web/20220721061150id_/https://petsymposium.org/popets/2022/popets-2022-0072.pdf\n", - "PoPETs\n", - "2022\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "FP2-MIA: A Membership Inference Attack Free of Posterior Probability in Machine Unlearning\n", - "https://link.springer.com/chapter/10.1007/978-3-031-20917-8_12\n", - "ProvSec\n", - "2022\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Deletion Inference, Reconstruction, and Compliance in Machine (Un)Learning\n", - "Un\n", - "PETS\n", - "2022\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Prompt Certified Machine Unlearning with Randomized Gradient Smoothing and Quantization\n", - "https://openreview.net/pdf?id=ue4gP8ZKiWb\n", - "NeurIPS\n", - "2022\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining\n", - "https://arxiv.org/abs/2203.07320\n", - "INFOCOM\n", - "2022\n", - "https://github.com/yiliucs/federated-unlearning\n", - "Model-Agnostic\n", - "----\n", - "Backdoor Defense with Machine Unlearning\n", - "https://arxiv.org/abs/2201.09538\n", - "INFOCOM\n", - "2022\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Markov Chain Monte Carlo-Based Machine Unlearning: Unlearning What Needs to be Forgotten\n", - "https://dl.acm.org/doi/abs/10.1145/3488932.3517406\n", - "ASIA CCS\n", - "2022\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Federated Unlearning for On-Device Recommendation\n", - "https://arxiv.org/abs/2210.10958\n", - "arXiv\n", - "2022\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher\n", - "https://arxiv.org/abs/2205.08096\n", - "arXiv\n", - "2022\n", - "-\n", - "Model-Agnostic\n", - "----\n", - " Efficient Two-Stage Model Retraining for Machine Unlearning\n", - "https://openaccess.thecvf.com/content/CVPR2022W/HCIS/html/Kim_Efficient_Two-Stage_Model_Retraining_for_Machine_Unlearning_CVPRW_2022_paper.html\n", - "CVPR Workshop\n", - "2022\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Learn to Forget: Machine Unlearning Via Neuron Masking\n", - "https://ieeexplore.ieee.org/abstract/document/9844865?casa_token=_eowH3BTt1sAAAAA:X0uCpLxOwcFRNJHoo3AtA0ay4t075_cSptgTMznsjusnvgySq-rJe8GC285YhWG4Q0fUmP9Sodw0\n", - "IEEE\n", - "2021\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Adaptive Machine Unlearning\n", - "https://proceedings.neurips.cc/paper/2021/hash/87f7ee4fdb57bdfd52179947211b7ebb-Abstract.html\n", - "NeurIPS\n", - "2021\n", - "https://github.com/ChrisWaites/adaptive-machine-unlearning\n", - "Model-Agnostic\n", - "----\n", - "Descent-to-Delete: Gradient-Based Methods for Machine Unlearning\n", - "https://proceedings.mlr.press/v132/neel21a.html\n", - "ALT\n", - "2021\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Remember What You Want to Forget: Algorithms for Machine Unlearning\n", - "https://arxiv.org/abs/2103.03279\n", - "NeurIPS\n", - "2021\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "FedEraser: Enabling Efficient Client-Level Data Removal from Federated Learning Models\n", - "https://ieeexplore.ieee.org/abstract/document/9521274\n", - "IWQoS\n", - "2021\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Federated Unlearning\n", - "https://arxiv.org/abs/2012.13891\n", - "IWQoS\n", - "2021\n", - "https://www.dropbox.com/s/1lhx962axovbbom/FedEraser-Code.zip?dl=0\n", - "Model-Agnostic\n", - "----\n", - "Machine Unlearning via Algorithmic Stability\n", - "https://proceedings.mlr.press/v134/ullah21a.html\n", - "COLT\n", - "2021\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "EMA: Auditing Data Removal from Trained Models\n", - "https://link.springer.com/chapter/10.1007/978-3-030-87240-3_76\n", - "MICCAI\n", - "2021\n", - "https://github.com/Hazelsuko07/EMA\n", - "Model-Agnostic\n", - "----\n", - "Knowledge-Adaptation Priors\n", - "https://proceedings.neurips.cc/paper/2021/hash/a4380923dd651c195b1631af7c829187-Abstract.html\n", - "NeurIPS\n", - "2021\n", - "https://github.com/team-approx-bayes/kpriors\n", - "Model-Agnostic\n", - "----\n", - "PrIU: A Provenance-Based Approach for Incrementally Updating Regression Models\n", - "https://dl.acm.org/doi/abs/10.1145/3318464.3380571\n", - "NeurIPS\n", - "2020\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks\n", - "https://arxiv.org/abs/1911.04933\n", - "CVPR\n", - "2020\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Learn to Forget: User-Level Memorization Elimination in Federated Learning\n", - "https://www.researchgate.net/profile/Ximeng-Liu-5/publication/340134612_Learn_to_Forget_User-Level_Memorization_Elimination_in_Federated_Learning/links/5e849e64a6fdcca789e5f955/Learn-to-Forget-User-Level-Memorization-Elimination-in-Federated-Learning.pdf\n", - "arXiv\n", - "2020\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Certified Data Removal from Machine Learning Models\n", - "https://proceedings.mlr.press/v119/guo20c.html\n", - "ICML\n", - "2020\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Class Clown: Data Redaction in Machine Unlearning at Enterprise Scale\n", - "https://arxiv.org/abs/2012.04699\n", - "arXiv\n", - "2020\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "A Novel Online Incremental and Decremental Learning Algorithm Based on Variable Support Vector Machine\n", - "https://link.springer.com/article/10.1007/s10586-018-1772-4\n", - "Cluster Computing\n", - "2019\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Making AI Forget You: Data Deletion in Machine Learning\n", - "https://papers.nips.cc/paper/2019/hash/cb79f8fa58b91d3af6c9c991f63962d3-Abstract.html\n", - "NeurIPS\n", - "2019\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Lifelong Anomaly Detection Through Unlearning\n", - "https://dl.acm.org/doi/abs/10.1145/3319535.3363226\n", - "CCS\n", - "2019\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Learning Not to Learn: Training Deep Neural Networks With Biased Data\n", - "https://openaccess.thecvf.com/content_CVPR_2019/html/Kim_Learning_Not_to_Learn_Training_Deep_Neural_Networks_With_Biased_CVPR_2019_paper.html\n", - "CVPR\n", - "2019\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Efficient Repair of Polluted Machine Learning Systems via Causal Unlearning\n", - "https://dl.acm.org/citation.cfm?id=3196517\n", - "ASIACCS\n", - "2018\n", - "https://github.com/CausalUnlearning/KARMA\n", - "Model-Agnostic\n", - "----\n", - "Understanding Black-box Predictions via Influence Functions\n", - "https://proceedings.mlr.press/v70/koh17a.html\n", - "ICML\n", - "2017\n", - "https://github.com/kohpangwei/influence-release\n", - "Model-Agnostic\n", - "----\n", - "Towards Making Systems Forget with Machine Unlearning\n", - "https://ieeexplore.ieee.org/abstract/document/7163042\n", - "S&P\n", - "2015\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Towards Making Systems Forget with Machine Unlearning\n", - "https://dl.acm.org/doi/10.1109/SP.2015.35\n", - "S&P\n", - "2015\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Incremental and decremental training for linear classification\n", - "https://dl.acm.org/doi/10.1145/2623330.2623661\n", - "KDD\n", - "2014\n", - "https://www.csie.ntu.edu.tw/~cjlin/papers/ws/\n", - "Model-Agnostic\n", - "----\n", - "Multiple Incremental Decremental Learning of Support Vector Machines\n", - "https://dl.acm.org/doi/10.5555/2984093.2984196\n", - "NIPS\n", - "2009\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Incremental and Decremental Learning for Linear Support Vector Machines\n", - "https://dl.acm.org/doi/10.5555/1776814.1776838\n", - "ICANN\n", - "2007\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Decremental Learning Algorithms for Nonlinear Langrangian and Least Squares Support Vector Machines\n", - "https://www.semanticscholar.org/paper/Decremental-Learning-Algorithms-for-Nonlinear-and-Duan-Li/312c677f0882d0dfd60bfd77346588f52aefd10f\n", - "OSB\n", - "2007\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Multicategory Incremental Proximal Support Vector Classifiers\n", - "https://link.springer.com/chapter/10.1007/978-3-540-45224-9_54\n", - "KES\n", - "2003\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Incremental and Decremental Proximal Support Vector Classification using Decay Coefficients\n", - "https://link.springer.com/chapter/10.1007/978-3-540-45228-7_42\n", - "DaWak\n", - "2003\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Incremental and Decremental Support Vector Machine Learning\n", - "https://dl.acm.org/doi/10.5555/3008751.3008808\n", - "NeurIPS\n", - "2000\n", - "-\n", - "Model-Agnostic\n", - "----\n", - "Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearning\n", - "https://arxiv.org/abs/2302.02069\n", - "WWW\n", - "2023\n", - "https://github.com/nju-websoft/FedLU/\n", - "Model-Intrinsic\n", - "----\n", - "One-Shot Machine Unlearning with Mnemonic Code\n", - "https://arxiv.org/abs/2306.05670\n", - "arXiv\n", - "2023\n", - "-\n", - "Model-Intrinsic\n", - "----\n", - "Inductive Graph Unlearning\n", - "https://arxiv.org/pdf/2304.03093.pdf\n", - "USENIX\n", - "2023\n", - "https://github.com/Happy2Git/GUIDE\n", - "Model-Intrinsic\n", - "----\n", - "ERM-KTP: Knowledge-level Machine Unlearning via Knowledge Transfer\n", - "https://openaccess.thecvf.com/content/CVPR2023/papers/Lin_ERM-KTP_Knowledge-Level_Machine_Unlearning_via_Knowledge_Transfer_CVPR_2023_paper.pdf\n", - "CVPR\n", - "2023\n", - "https://github.com/RUIYUN-ML/ERM-KTP\n", - "Model-Intrinsic\n", - "----\n", - "GNNDelete: A General Strategy for Unlearning in Graph Neural Networks\n", - "https://arxiv.org/abs/2302.13406\n", - "ICLR\n", - "2023\n", - "https://github.com/mims-harvard/GNNDelete\n", - "Model-Intrinsic\n", - "----\n", - "Unfolded Self-Reconstruction LSH: Towards Machine Unlearning in Approximate Nearest Neighbour Search\n", - "https://arxiv.org/pdf/2304.02350.pdf\n", - "arXiv\n", - "2023\n", - "https://anonymous.4open.science/r/ann-benchmarks-3786/README.md\n", - "Model-Intrinsic\n", - "----\n", - "Efficiently Forgetting What You Have Learned in Graph Representation Learning via Projection\n", - "https://arxiv.org/abs/2302.08990\n", - "AISTATS\n", - "2023\n", - "https://github.com/CongWeilin/Projector\n", - "Model-Intrinsic\n", - "----\n", - "Unrolling SGD: Understanding Factors Influencing Machine Unlearning\n", - "https://ieeexplore.ieee.org/abstract/document/9797378\n", - "EuroS&P\n", - "2022\n", - "https://github.com/cleverhans-lab/unrolling-sgd\n", - "Model-Intrinsic\n", - "----\n", - "Graph Unlearning\n", - "https://arxiv.org/abs/2103.14991\n", - "CCS\n", - "2022\n", - "https://github.com/MinChen00/Graph-Unlearning\n", - "Model-Intrinsic\n", - "----\n", - "Certified Graph Unlearning\n", - "https://arxiv.org/abs/2206.09140\n", - "GLFrontiers Workshop\n", - "2022\n", - "https://github.com/thupchnsky/sgc_unlearn\n", - "Model-Intrinsic\n", - "----\n", - "Skin Deep Unlearning: Artefact and Instrument Debiasing in the Context of Melanoma Classification\n", - "https://arxiv.org/abs/2109.09818\n", - "ICML\n", - "2022\n", - "https://github.com/pbevan1/Skin-Deep-Unlearning\n", - "Model-Intrinsic\n", - "----\n", - "Near-Optimal Task Selection for Meta-Learning with Mutual Information and Online Variational Bayesian Unlearning\n", - "https://proceedings.mlr.press/v151/chen22h.html\n", - "AISTATS\n", - "2022\n", - "-\n", - "Model-Intrinsic\n", - "----\n", - "Unlearning Protected User Attributes in Recommendations with Adversarial Training\n", - "https://arxiv.org/abs/2206.04500\n", - "SIGIR\n", - "2022\n", - "https://github.com/CPJKU/adv-multvae\n", - "Model-Intrinsic\n", - "----\n", - "Recommendation Unlearning\n", - "https://dl.acm.org/doi/abs/10.1145/3485447.3511997\n", - "TheWebConf\n", - "2022\n", - "https://github.com/chenchongthu/Recommendation-Unlearning\n", - "Model-Intrinsic\n", - "----\n", - "Knowledge Neurons in Pretrained Transformers\n", - "https://arxiv.org/abs/2104.08696\n", - "ACL\n", - "2022\n", - "https://github.com/Hunter-DDM/knowledge-neurons\n", - "Model-Intrinsic\n", - "----\n", - "Memory-Based Model Editing at Scale\n", - "https://proceedings.mlr.press/v162/mitchell22a/mitchell22a.pdf\n", - "MLR\n", - "2022\n", - "https://sites.google.com/view/serac-editing\n", - "Model-Intrinsic\n", - "----\n", - "Forgetting Fast in Recommender Systems\n", - "https://arxiv.org/abs/2208.06875\n", - "arXiv\n", - "2022\n", - "-\n", - "Model-Intrinsic\n", - "----\n", - "Unlearning Nonlinear Graph Classifiers in the Limited Training Data Regime\n", - "https://arxiv.org/abs/2211.03216\n", - "arXiv\n", - "2022\n", - "-\n", - "Model-Intrinsic\n", - "----\n", - "Deep Regression Unlearning\n", - "https://arxiv.org/abs/2210.08196\n", - "arXiv\n", - "2022\n", - "-\n", - "Model-Intrinsic\n", - "----\n", - "Quark: Controllable Text Generation with Reinforced Unlearning\n", - "https://arxiv.org/abs/2205.13636\n", - "arXiv\n", - "2022\n", - "https://github.com/GXimingLu/Quark\n", - "Model-Intrinsic\n", - "----\n", - "Forget-SVGD: Particle-Based Bayesian Federated Unlearning\n", - "https://ieeexplore.ieee.org/abstract/document/9820602\n", - "DSL Workshop\n", - "2022\n", - "-\n", - "Model-Intrinsic\n", - "----\n", - "Machine Unlearning of Federated Clusters\n", - "https://arxiv.org/abs/2210.16424\n", - "arXiv\n", - "2022\n", - "-\n", - "Model-Intrinsic\n", - "----\n", - "Machine Unlearning for Image Retrieval: A Generative Scrubbing Approach\n", - "https://dl.acm.org/doi/abs/10.1145/3503161.3548378\n", - "MM\n", - "2022\n", - "-\n", - "Model-Intrinsic\n", - "----\n", - "Machine Unlearning: Linear Filtration for Logit-based Classifiers\n", - "https://link.springer.com/article/10.1007/s10994-022-06178-9\n", - "Machine Learning\n", - "2022\n", - "-\n", - "Model-Intrinsic\n", - "----\n", - "Deep Unlearning via Randomized Conditionally Independent Hessians\n", - "https://openaccess.thecvf.com/content/CVPR2022/html/Mehta_Deep_Unlearning_via_Randomized_Conditionally_Independent_Hessians_CVPR_2022_paper.html\n", - "CVPR\n", - "2022\n", - "https://github.com/vsingh-group/LCODEC-deep-unlearning\n", - "Model-Intrinsic\n", - "----\n", - "Challenges and Pitfalls of Bayesian Unlearning\n", - "https://arxiv.org/abs/2207.03227\n", - "UPML Workshop\n", - "2022\n", - "-\n", - "Model-Intrinsic\n", - "----\n", - "Federated Unlearning via Class-Discriminative Pruning\n", - "https://arxiv.org/abs/2110.11794\n", - "WWW\n", - "2022\n", - "-\n", - "Model-Intrinsic\n", - "----\n", - "Active forgetting via influence estimation for neural networks\n", - "https://onlinelibrary.wiley.com/doi/abs/10.1002/int.22981\n", - "Int. J. Intel. Systems\n", - "2022\n", - "-\n", - "Model-Intrinsic\n", - "----\n", - "Variational Bayesian unlearning\n", - "https://dl.acm.org/doi/abs/10.5555/3495724.3497068\n", - "NeurIPS\n", - "2022\n", - "-\n", - "Model-Intrinsic\n", - "----\n", - "Revisiting Machine Learning Training Process for Enhanced Data Privacy\n", - "https://dl.acm.org/doi/abs/10.1145/3474124.3474208\n", - "IC3\n", - "2021\n", - "-\n", - "Model-Intrinsic\n", - "----\n", - "Knowledge Removal in Sampling-based Bayesian Inference\n", - "https://openreview.net/forum?id=dTqOcTUOQO\n", - "ICLR\n", - "2021\n", - "https://github.com/fshp971/mcmc-unlearning\n", - "Model-Intrinsic\n", - "----\n", - "Mixed-Privacy Forgetting in Deep Networks\n", - "https://openaccess.thecvf.com/content/CVPR2021/html/Golatkar_Mixed-Privacy_Forgetting_in_Deep_Networks_CVPR_2021_paper.html\n", - "CVPR\n", - "2021\n", - "-\n", - "Model-Intrinsic\n", - "----\n", - "HedgeCut: Maintaining Randomised Trees for Low-Latency Machine Unlearning\n", - "https://dl.acm.org/doi/abs/10.1145/3448016.3457239\n", - "SIGMOD\n", - "2021\n", - "https://github.com/schelterlabs/hedgecut\n", - "Model-Intrinsic\n", - "----\n", - "A Unified PAC-Bayesian Framework for Machine Unlearning via Information Risk Minimization\n", - "https://ieeexplore.ieee.org/abstract/document/9596170\n", - "MLSP\n", - "2021\n", - "-\n", - "Model-Intrinsic\n", - "----\n", - "DeepObliviate: A Powerful Charm for Erasing Data Residual Memory in Deep Neural Networks\n", - "https://arxiv.org/abs/2105.06209\n", - "arXiv\n", - "2021\n", - "-\n", - "Model-Intrinsic\n", - "----\n", - "Approximate Data Deletion from Machine Learning Models: Algorithms and Evaluations\n", - "https://arxiv.org/abs/2002.10077\n", - "AISTATS\n", - "2021\n", - "https://github.com/zleizzo/datadeletion\n", - "Model-Intrinsic\n", - "----\n", - "Bayesian Inference Forgetting\n", - "https://arxiv.org/abs/2101.06417\n", - "arXiv\n", - "2021\n", - "https://github.com/fshp971/BIF\n", - "Model-Intrinsic\n", - "----\n", - "Approximate Data Deletion from Machine Learning Models\n", - "https://proceedings.mlr.press/v130/izzo21a.html\n", - "AISTATS\n", - "2021\n", - "https://github.com/zleizzo/datadeletion\n", - "Model-Intrinsic\n", - "----\n", - "Online Forgetting Process for Linear Regression Models\n", - "https://proceedings.mlr.press/v130/li21a.html\n", - "AISTATS\n", - "2021\n", - "-\n", - "Model-Intrinsic\n", - "----\n", - "RevFRF: Enabling Cross-domain Random Forest Training with Revocable Federated Learning\n", - "https://ieeexplore.ieee.org/abstract/document/9514457\n", - "IEEE\n", - "2021\n", - "-\n", - "Model-Intrinsic\n", - "----\n", - "Coded Machine Unlearning\n", - "https://ieeexplore.ieee.org/abstract/document/9458237\n", - "IEEE Access\n", - "2021\n", - "-\n", - "Model-Intrinsic\n", - "----\n", - "Machine Unlearning for Random Forests\n", - "http://proceedings.mlr.press/v139/brophy21a.html\n", - "ICML\n", - "2021\n", - "-\n", - "Model-Intrinsic\n", - "----\n", - "Bayesian Variational Federated Learning and Unlearning in Decentralized Networks\n", - "https://ieeexplore.ieee.org/abstract/document/9593225\n", - "SPAWC\n", - "2021\n", - "-\n", - "Model-Intrinsic\n", - "----\n", - "Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations\n", - "https://link.springer.com/chapter/10.1007/978-3-030-58526-6_23\n", - "ECCV\n", - "2020\n", - "-\n", - "Model-Intrinsic\n", - "----\n", - "Influence Functions in Deep Learning Are Fragile\n", - "https://www.semanticscholar.org/paper/Influence-Functions-in-Deep-Learning-Are-Fragile-Basu-Pope/098076a2c90e42c81b843bf339446427c2ff02ed\n", - "arXiv\n", - "2020\n", - "-\n", - "Model-Intrinsic\n", - "----\n", - "Deep Autoencoding Topic Model With Scalable Hybrid Bayesian Inference\n", - "https://ieeexplore.ieee.org/document/9121755\n", - "IEEE\n", - "2020\n", - "-\n", - "Model-Intrinsic\n", - "----\n", - "Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks\n", - "https://arxiv.org/abs/1911.04933\n", - "CVPR\n", - "2020\n", - "-\n", - "Model-Intrinsic\n", - "----\n", - "Uncertainty in Neural Networks: Approximately Bayesian Ensembling\n", - "https://proceedings.mlr.press/v108/pearce20a.html\n", - "AISTATS\n", - "2020\n", - "https://teapearce.github.io/portfolio/github_io_1_ens/\n", - "Model-Intrinsic\n", - "----\n", - "Certified Data Removal from Machine Learning Models\n", - "https://proceedings.mlr.press/v119/guo20c.html\n", - "ICML\n", - "2020\n", - "-\n", - "Model-Intrinsic\n", - "----\n", - "DeltaGrad: Rapid retraining of machine learning models\n", - "https://proceedings.mlr.press/v119/wu20b.html\n", - "ICML\n", - "2020\n", - "https://github.com/thuwuyinjun/DeltaGrad\n", - "Model-Intrinsic\n", - "----\n", - "Making AI Forget You: Data Deletion in Machine Learning\n", - "https://papers.nips.cc/paper/2019/hash/cb79f8fa58b91d3af6c9c991f63962d3-Abstract.html\n", - "NeurIPS\n", - "2019\n", - "-\n", - "Model-Intrinsic\n", - "----\n", - "“Amnesia” – Towards Machine Learning Models That Can Forget User Data Very Fast\n", - "http://cidrdb.org/cidr2020/papers/p32-schelter-cidr20.pdf\n", - "AIDB Workshop\n", - "2019\n", - "https://github.com/schelterlabs/projects-amnesia\n", - "Model-Intrinsic\n", - "----\n", - "A Novel Online Incremental and Decremental Learning Algorithm Based on Variable Support Vector Machine\n", - "https://link.springer.com/article/10.1007/s10586-018-1772-4\n", - "Cluster Computing\n", - "2019\n", - "-\n", - "Model-Intrinsic\n", - "----\n", - "Neural Text Degeneration With Unlikelihood Training\n", - "https://arxiv.org/abs/1908.04319\n", - "arXiv\n", - "2019\n", - "https://github.com/facebookresearch/unlikelihood_training\n", - "Model-Intrinsic\n", - "----\n", - "Bayesian Neural Networks with Weight Sharing Using Dirichlet Processes\n", - "https://ieeexplore.ieee.org/document/8566011\n", - "IEEE\n", - "2018\n", - "https://github.com/wroth8/dp-bnn\n", - "Model-Intrinsic\n", - "----\n", - "Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks\n", - "https://arxiv.org/abs/2212.10717\n", - "NeurIPS-TSRML\n", - "2022\n", - "https://github.com/Jimmy-di/camouflage-poisoning\n", - "Data-Driven\n", - "----\n", - "Forget Unlearning: Towards True Data Deletion in Machine Learning\n", - "https://arxiv.org/pdf/2210.08911.pdf\n", - "ICLR\n", - "2022\n", - "-\n", - "Data-Driven\n", - "----\n", - "ARCANE: An Efficient Architecture for Exact Machine Unlearning\n", - "https://www.ijcai.org/proceedings/2022/0556.pdf\n", - "IJCAI\n", - "2022\n", - "-\n", - "Data-Driven\n", - "----\n", - "PUMA: Performance Unchanged Model Augmentation for Training Data Removal\n", - "https://ojs.aaai.org/index.php/AAAI/article/view/20846\n", - "AAAI\n", - "2022\n", - "-\n", - "Data-Driven\n", - "----\n", - "Certifiable Unlearning Pipelines for Logistic Regression: An Experimental Study\n", - "https://www.mdpi.com/2504-4990/4/3/28\n", - "MAKE\n", - "2022\n", - "https://version.helsinki.fi/mahadeva/unlearning-experiments\n", - "Data-Driven\n", - "----\n", - "Zero-Shot Machine Unlearning\n", - "https://arxiv.org/abs/2201.05629\n", - "arXiv\n", - "2022\n", - "-\n", - "Data-Driven\n", - "----\n", - "GRAPHEDITOR: An Efficient Graph Representation Learning and Unlearning Approach\n", - "https://congweilin.github.io/CongWeilin.io/files/GraphEditor.pdf\n", - "-\n", - "2022\n", - "https://anonymous.4open.science/r/GraphEditor-NeurIPS22-856E/README.md\n", - "Data-Driven\n", - "----\n", - "Fast Model Update for IoT Traffic Anomaly Detection with Machine Unlearning\n", - "https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9927728\n", - "IEEE IoT-J\n", - "2022\n", - "-\n", - "Data-Driven\n", - "----\n", - "Learning to Refit for Convex Learning Problems\n", - "https://arxiv.org/abs/2111.12545\n", - "arXiv\n", - "2021\n", - "-\n", - "Data-Driven\n", - "----\n", - "Fast Yet Effective Machine Unlearning\n", - "https://arxiv.org/abs/2111.08947\n", - "arXiv\n", - "2021\n", - "-\n", - "Data-Driven\n", - "----\n", - "Learning with Selective Forgetting\n", - "https://www.ijcai.org/proceedings/2021/0137.pdf\n", - "IJCAI\n", - "2021\n", - "-\n", - "Data-Driven\n", - "----\n", - "SSSE: Efficiently Erasing Samples from Trained Machine Learning Models\n", - "https://openreview.net/forum?id=GRMKEx3kEo\n", - "NeurIPS-PRIML\n", - "2021\n", - "-\n", - "Data-Driven\n", - "----\n", - "How Does Data Augmentation Affect Privacy in Machine Learning?\n", - "https://arxiv.org/abs/2007.10567\n", - "AAAI\n", - "2021\n", - "https://github.com/dayu11/MI_with_DA\n", - "Data-Driven\n", - "----\n", - "Coded Machine Unlearning\n", - "https://ieeexplore.ieee.org/document/9458237\n", - "IEEE\n", - "2021\n", - "-\n", - "Data-Driven\n", - "----\n", - "Machine Unlearning\n", - "https://ieeexplore.ieee.org/document/9519428\n", - "IEEE\n", - "2021\n", - "https://github.com/cleverhans-lab/machine-unlearning\n", - "Data-Driven\n", - "----\n", - "How Does Data Augmentation Affect Privacy in Machine Learning?\n", - "https://ojs.aaai.org/index.php/AAAI/article/view/17284/\n", - "AAAI\n", - "2021\n", - "https://github.com/dayu11/MI_with_DA\n", - "Data-Driven\n", - "----\n", - "Amnesiac Machine Learning\n", - "https://ojs.aaai.org/index.php/AAAI/article/view/17371\n", - "AAAI\n", - "2021\n", - "https://github.com/lmgraves/AmnesiacML\n", - "Data-Driven\n", - "----\n", - "Unlearnable Examples: Making Personal Data Unexploitable\n", - "https://arxiv.org/abs/2101.04898\n", - "ICLR\n", - "2021\n", - "https://github.com/HanxunH/Unlearnable-Examples\n", - "Data-Driven\n", - "----\n", - "Descent-to-Delete: Gradient-Based Methods for Machine Unlearning\n", - "https://proceedings.mlr.press/v132/neel21a.html\n", - "ALT\n", - "2021\n", - "-\n", - "Data-Driven\n", - "----\n", - "Fawkes: Protecting Privacy against Unauthorized Deep Learning Models\n", - "https://dl.acm.org/doi/abs/10.5555/3489212.3489302\n", - "USENIX Sec. Sym.\n", - "2020\n", - "https://github.com/Shawn-Shan/fawkes\n", - "Data-Driven\n", - "----\n", - "PrIU: A Provenance-Based Approach for Incrementally Updating Regression Models\n", - "https://dl.acm.org/doi/abs/10.1145/3318464.3380571\n", - "SIGMOD\n", - "2020\n", - "-\n", - "Data-Driven\n", - "----\n", - "DeltaGrad: Rapid retraining of machine learning models\n", - "https://proceedings.mlr.press/v119/wu20b.html\n", - "ICML\n", - "2020\n", - "https://github.com/thuwuyinjun/DeltaGrad\n", - "Data-Driven\n" - ] - } - ], + "outputs": [], "source": [ - "for line in lines:\n", - " if line==\"Model-Agnostic\\n\" or line==\"Model-Intrinsic\\n\" or line==\"Data-Driven\\n\":\n", - " types=line[:-1]\n", - " else:\n", - " print('----')\n", - " ### title\n", - " title = re.search(r'\\[(.*?)\\]', line).group()[1:-1]\n", - "\n", - " ### link to paper\n", - " link = re.search(r'\\((.*?)\\)', line).group()[1:-1]\n", - "\n", - " try:\n", - " ### venue\n", - " venue = re.search(r'\\|\\s\\_(.*?)\\_', line).group()[3:-1]\n", - " except:\n", - " venue = '-'\n", - "\n", - " ### year\n", - " year = re.search(r'\\s\\d{4}\\s', line).group()[1:-1]\n", - "\n", - " ### code\n", - " res = re.search(r'\\]\\]\\((.*?)\\)', line)\n", - " if res is None:\n", - " code = '-'\n", - " else:\n", - " code = res.group()[3:-1]\n", - "\n", - "# ### type\n", - "# type_slash_idx = findOccurrences(line, '|')[-2:]\n", - "# types = line[type_slash_idx[0]:type_slash_idx[1]][2:-1].lstrip()\n", + "import re\n", "\n", - " print(title)\n", - " print(link)\n", - " print(venue)\n", - " print(year)\n", - " print(code)\n", - " print(types)\n", + "def markdown_to_html(input_file, output_file):\n", + " with open(input_file, 'r') as md, open(output_file, 'w') as html:\n", + " html.write('\\n') # Start of HTML table\n", + " \n", + " for line in md:\n", + " # Ignore empty lines and lines that do not contain markdown table syntax\n", + " if '|' not in line.strip():\n", + " continue\n", + " \n", + " # Split the line into columns based on '|' and strip whitespace\n", + " columns = [col.strip() for col in line.split('|') if col.strip()]\n", + " \n", + " # Start of the table row\n", + " html.write(' \\n')\n", + " \n", + " # Loop through columns and handle each type of data\n", + " for idx, col in enumerate(columns):\n", + " if idx == 0: # First column with link and title\n", + " match = re.search(r'\\[(.*?)\\]\\((.*?)\\)', col)\n", + " if match:\n", + " title = match.group(1)\n", + " link = match.group(2)\n", + " html.write(f' \\n')\n", + " else:\n", + " html.write(' \\n')\n", + " elif idx == 6: # Last column might have a code link\n", + " code_match = re.search(r'\\[(.*?)\\]\\((.*?)\\)', col)\n", + " if code_match:\n", + " code_link = code_match.group(2)\n", + " html.write(f' \\n')\n", + " else:\n", + " html.write(' \\n')\n", + " else: # Other columns\n", + " col = col.replace('_', '').strip() # Remove markdown italic markers\n", + " if col == '-': # If column is explicitly empty, maintain the placeholder\n", + " html.write(' \\n')\n", + " elif not col: # If column is empty, output a placeholder with 'code' class\n", + " html.write(' \\n')\n", + " else:\n", + " html.write(f' \\n')\n", + " \n", + " # End of the table row\n", + " html.write(' \\n')\n", + " \n", + " html.write('
{title}-[Code]---{col}
') # End of HTML table\n", "\n", - " ### formation\n", - " f.write(\" \")\n", - " f.write(\"\\n\")\n", - " f.write(\" {}\".format(link, title))\n", - " f.write(\"\\n\")\n", - " f.write(\" {}\".format(venue))\n", - " f.write(\"\\n\")\n", - " f.write(\" {}\".format(year))\n", - " f.write(\"\\n\")\n", - " if code == '-':\n", - " f.write(\" -\".format(code))\n", - " else:\n", - " f.write(\" [Code]\".format(code))\n", - " f.write(\"\\n\")\n", - " f.write(\" {}\".format(types))\n", - " f.write(\"\\n\")\n", - " f.write(\" \")\n", - " f.write(\"\\n\")\n", - " \n", - "f.close()" + "# Usage\n", + "markdown_to_html('input.txt', 'output.txt')\n" ] }, { @@ -1087,7 +106,7 @@ ], "metadata": { "kernelspec": { - "display_name": "Python 3 (ipykernel)", + "display_name": "Python 3", "language": "python", "name": "python3" },